DiagSplat · train-only no-reference mask construction
Fountain:强视觉语义框 → SAM 中间结果
每张 train 图独立查看;强视觉判断负责列出 transient 人与随身物,SAM 2.1 只负责像素轮廓。Raw residual 仅是辅助,低 residual 不能否定 transient。17 张 test 完全未参与。
141 transient masks · 27 clean routes · 下一步为逐帧边界安全带 critic。
no_prominent_transient · 0 semantic box(es) · raw 0.00% · route 0.00%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6393",
"cause": "no_prominent_transient",
"agent_record": null,
"boxes_xyxy": [],
"sam_predicted_iou": [],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6393.png",
"routing_mask_path": "masks/IMG_6393_routing.png",
"raw_mask_fraction": 0.0,
"routing_mask_fraction": 0.0
}
no_prominent_transient · 0 semantic box(es) · raw 0.00% · route 0.00%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6394",
"cause": "no_prominent_transient",
"agent_record": null,
"boxes_xyxy": [],
"sam_predicted_iou": [],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6394.png",
"routing_mask_path": "masks/IMG_6394_routing.png",
"raw_mask_fraction": 0.0,
"routing_mask_fraction": 0.0
}
transient_person · 1 semantic box(es) · raw 1.20% · route 2.10%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6395",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6395",
"boxes_norm_xyxy": [
[
0.9008,
0.5132,
1,
0.8492
]
],
"description": "画面右缘仅部分可见的人及黑色手提袋",
"confidence": 0.82
},
"boxes_xyxy": [
[
454.0032043457031,
193.98959350585938,
504.0,
320.9975891113281
]
],
"sam_predicted_iou": [
0.83984375
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6395.png",
"routing_mask_path": "masks/IMG_6395_routing.png",
"raw_mask_fraction": 0.012030738221214412,
"routing_mask_fraction": 0.020964558662971363
}
transient_person · 1 semantic box(es) · raw 2.49% · route 3.45%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6396",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6396",
"boxes_norm_xyxy": [
[
0.8869,
0.2381,
1,
0.7169
]
],
"description": "右缘行人及其黑色手提袋,身体被画面裁切",
"confidence": 0.94
},
"boxes_xyxy": [
[
446.9975891113281,
90.00180053710938,
504.0,
270.9881896972656
]
],
"sam_predicted_iou": [
0.90234375
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6396.png",
"routing_mask_path": "masks/IMG_6396_routing.png",
"raw_mask_fraction": 0.02493281263122533,
"routing_mask_fraction": 0.034549004787100025
}
transient_person · 1 semantic box(es) · raw 2.41% · route 3.16%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6397",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6397",
"boxes_norm_xyxy": [
[
0.871,
0.3466,
1,
0.8122
]
],
"description": "右缘被裁切的行人及黑色手提袋",
"confidence": 0.88
},
"boxes_xyxy": [
[
438.9840087890625,
131.01480102539062,
504.0,
307.0115966796875
]
],
"sam_predicted_iou": [
0.87890625
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6397.png",
"routing_mask_path": "masks/IMG_6397_routing.png",
"raw_mask_fraction": 0.024056227429243304,
"routing_mask_fraction": 0.031588561350466116
}
transient_person · 1 semantic box(es) · raw 19.05% · route 22.12%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6398",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6398",
"boxes_norm_xyxy": [
[
0.1508,
0.0714,
0.5119,
1
]
],
"description": "近景行人,含大号黑色背包与手中黑袋",
"confidence": 0.99
},
"boxes_xyxy": [
[
76.0031967163086,
26.989200592041016,
257.9975891113281,
378.0
]
],
"sam_predicted_iou": [
0.953125
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6398.png",
"routing_mask_path": "masks/IMG_6398_routing.png",
"raw_mask_fraction": 0.1905076845553036,
"routing_mask_fraction": 0.221172419585118
}
transient_person · 1 semantic box(es) · raw 4.92% · route 6.48%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6399",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6399",
"boxes_norm_xyxy": [
[
0,
0.1455,
0.2381,
0.7407
]
],
"description": "左缘有清晰近景行人,含背包及手提袋。",
"confidence": 0.9
},
"boxes_xyxy": [
[
0.0,
54.999000549316406,
120.00240325927734,
279.9845886230469
]
],
"sam_predicted_iou": [
0.875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6399.png",
"routing_mask_path": "masks/IMG_6399_routing.png",
"raw_mask_fraction": 0.049162257495590826,
"routing_mask_fraction": 0.06483056185437137
}
transient_person · 1 semantic box(es) · raw 0.70% · route 2.01%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6400",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6400",
"boxes_norm_xyxy": [
[
0.5417,
0.1481,
0.6627,
0.5026
]
],
"description": "雕塑后方有被遮挡但清晰可辨的行人及背包。",
"confidence": 0.9
},
"boxes_xyxy": [
[
273.0168151855469,
55.9818000793457,
334.00079345703125,
189.98280334472656
]
],
"sam_predicted_iou": [
0.59375
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6400.png",
"routing_mask_path": "masks/IMG_6400_routing.png",
"raw_mask_fraction": 0.00701793062904174,
"routing_mask_fraction": 0.02010896951373142
}
transient_person · 1 semantic box(es) · raw 0.14% · route 1.30%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6401",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6401",
"boxes_norm_xyxy": [
[
0.7956,
0.2513,
0.9544,
0.5979
]
],
"description": "喷泉后方行人,含背包与手提袋",
"confidence": 0.96
},
"boxes_xyxy": [
[
400.9823913574219,
94.99140167236328,
481.0176086425781,
226.00619506835938
]
],
"sam_predicted_iou": [
0.54296875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6401.png",
"routing_mask_path": "masks/IMG_6401_routing.png",
"raw_mask_fraction": 0.0014119845469051818,
"routing_mask_fraction": 0.013017552700092383
}
transient_person · 1 semantic box(es) · raw 4.09% · route 5.85%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6402",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6402",
"boxes_norm_xyxy": [
[
0.7976,
0.2963,
1,
1
]
],
"description": "右缘被裁切的行人及黑色手提袋",
"confidence": 0.94
},
"boxes_xyxy": [
[
401.9903869628906,
112.00140380859375,
504.0,
378.0
]
],
"sam_predicted_iou": [
0.953125
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6402.png",
"routing_mask_path": "masks/IMG_6402_routing.png",
"raw_mask_fraction": 0.040853069622910895,
"routing_mask_fraction": 0.05846875787351978
}
transient_person · 1 semantic box(es) · raw 17.19% · route 18.85%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6403",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6403",
"boxes_norm_xyxy": [
[
0,
0.0529,
0.2718,
1
]
],
"description": "左侧近景行人,含大号背包与手提袋",
"confidence": 0.99
},
"boxes_xyxy": [
[
0.0,
19.996200561523438,
136.98719787597656,
378.0
]
],
"sam_predicted_iou": [
0.9765625
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6403.png",
"routing_mask_path": "masks/IMG_6403_routing.png",
"raw_mask_fraction": 0.17188418577307465,
"routing_mask_fraction": 0.18850781053162005
}
transient_person · 1 semantic box(es) · raw 4.61% · route 6.45%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6404",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6404",
"boxes_norm_xyxy": [
[
0.0179,
0.2646,
0.2242,
0.8095
]
],
"description": "左侧完整行人,含背包与手提袋",
"confidence": 0.98
},
"boxes_xyxy": [
[
9.021599769592285,
100.018798828125,
112.9968032836914,
305.9909973144531
]
],
"sam_predicted_iou": [
0.921875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6404.png",
"routing_mask_path": "masks/IMG_6404_routing.png",
"raw_mask_fraction": 0.046060090702947844,
"routing_mask_fraction": 0.06452611908961116
}
transient_person · 1 semantic box(es) · raw 1.04% · route 1.61%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6405",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6405",
"boxes_norm_xyxy": [
[
0.4206,
0.328,
0.5357,
0.5503
]
],
"description": "喷泉后方被遮挡的行人及背包",
"confidence": 0.94
},
"boxes_xyxy": [
[
211.98240661621094,
123.98400115966797,
269.9927978515625,
208.01339721679688
]
],
"sam_predicted_iou": [
0.8125
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6405.png",
"routing_mask_path": "masks/IMG_6405_routing.png",
"raw_mask_fraction": 0.010408793146888385,
"routing_mask_fraction": 0.01605148232132359
}
transient_person · 1 semantic box(es) · raw 0.30% · route 0.76%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6406",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6406",
"boxes_norm_xyxy": [
[
0.2361,
0.2619,
0.3591,
0.5079
]
],
"description": "喷泉后方被遮挡的行人及背包",
"confidence": 0.94
},
"boxes_xyxy": [
[
118.99440002441406,
98.99819946289062,
180.9864044189453,
191.9862060546875
]
],
"sam_predicted_iou": [
0.68359375
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6406.png",
"routing_mask_path": "masks/IMG_6406_routing.png",
"raw_mask_fraction": 0.0030286806080456873,
"routing_mask_fraction": 0.0075953220794490635
}
transient_person · 2 semantic box(es) · raw 3.12% · route 4.55%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6407",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6407",
"boxes_norm_xyxy": [
[
0,
0.2328,
0.127,
0.664
],
[
0.0853,
0.2169,
0.1468,
0.3545
]
],
"description": "左缘主要行人及其背包,另含后方较小行人",
"confidence": 0.86
},
"boxes_xyxy": [
[
0.0,
87.99839782714844,
64.00800323486328,
250.99200439453125
],
[
42.9911994934082,
81.98819732666016,
73.98719787597656,
134.00100708007812
]
],
"sam_predicted_iou": [
0.9375,
0.765625
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6407.png",
"routing_mask_path": "masks/IMG_6407_routing.png",
"raw_mask_fraction": 0.031189636348366506,
"routing_mask_fraction": 0.04549319727891157
}
transient_person · 2 semantic box(es) · raw 3.11% · route 4.67%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6408",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6408",
"boxes_norm_xyxy": [
[
0.129,
0.1772,
0.2877,
0.6296
],
[
0,
0.1931,
0.0218,
0.3069
]
],
"description": "左侧主要行人及手提袋;最左缘另有被裁切远景行人",
"confidence": 0.88
},
"boxes_xyxy": [
[
65.01599884033203,
66.98159790039062,
145.00079345703125,
237.98880004882812
],
[
0.0,
72.9917984008789,
10.987199783325195,
116.0082015991211
]
],
"sam_predicted_iou": [
0.9296875,
0.75390625
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6408.png",
"routing_mask_path": "masks/IMG_6408_routing.png",
"raw_mask_fraction": 0.031121399176954733,
"routing_mask_fraction": 0.04670047031158142
}
transient_person · 2 semantic box(es) · raw 3.23% · route 5.25%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6409",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6409",
"boxes_norm_xyxy": [
[
0.2004,
0.1693,
0.4067,
0.6402
],
[
0.3968,
0.2037,
0.4345,
0.3016
]
],
"description": "主要行人及黑袋,另含远景小行人",
"confidence": 0.95
},
"boxes_xyxy": [
[
101.00160217285156,
63.995399475097656,
204.976806640625,
241.99560546875
],
[
199.98719787597656,
76.99859619140625,
218.98800659179688,
114.00479888916016
]
],
"sam_predicted_iou": [
0.91015625,
0.87890625
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6409.png",
"routing_mask_path": "masks/IMG_6409_routing.png",
"raw_mask_fraction": 0.03226043503821282,
"routing_mask_fraction": 0.052495380868396745
}
transient_person · 2 semantic box(es) · raw 4.06% · route 5.99%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6410",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6410",
"boxes_norm_xyxy": [
[
0.0119,
0.1984,
0.2103,
0.7407
],
[
0,
0.2698,
0.0258,
0.373
]
],
"description": "左侧主要行人及黑袋;左缘另有被裁切远景行人",
"confidence": 0.9
},
"boxes_xyxy": [
[
5.997600078582764,
74.99520111083984,
105.99120330810547,
279.9845886230469
],
[
0.0,
101.9843978881836,
13.003199577331543,
140.99400329589844
]
],
"sam_predicted_iou": [
0.9140625,
0.81640625
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6410.png",
"routing_mask_path": "masks/IMG_6410_routing.png",
"raw_mask_fraction": 0.04055387587133619,
"routing_mask_fraction": 0.05988074242042496
}
no_prominent_transient · 0 semantic box(es) · raw 0.00% · route 0.00%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6411",
"cause": "no_prominent_transient",
"agent_record": null,
"boxes_xyxy": [],
"sam_predicted_iou": [],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6411.png",
"routing_mask_path": "masks/IMG_6411_routing.png",
"raw_mask_fraction": 0.0,
"routing_mask_fraction": 0.0
}
no_prominent_transient · 0 semantic box(es) · raw 0.00% · route 0.00%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6412",
"cause": "no_prominent_transient",
"agent_record": null,
"boxes_xyxy": [],
"sam_predicted_iou": [],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6412.png",
"routing_mask_path": "masks/IMG_6412_routing.png",
"raw_mask_fraction": 0.0,
"routing_mask_fraction": 0.0
}
transient_person · 1 semantic box(es) · raw 3.53% · route 5.11%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6413",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6413",
"boxes_norm_xyxy": [
[
0.7044,
0.2222,
0.8968,
0.7381
]
],
"description": "右侧行人,含大号背包与黑色手提袋",
"confidence": 0.99
},
"boxes_xyxy": [
[
355.0176086425781,
83.9916000366211,
451.9872131347656,
279.0018005371094
]
],
"sam_predicted_iou": [
0.9296875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6413.png",
"routing_mask_path": "masks/IMG_6413_routing.png",
"raw_mask_fraction": 0.035257621567145375,
"routing_mask_fraction": 0.05113063744016125
}
transient_person · 1 semantic box(es) · raw 1.73% · route 2.65%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6414",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6414",
"boxes_norm_xyxy": [
[
0.5516,
0.4524,
0.6548,
0.8122
]
],
"description": "喷泉后方行人及背包",
"confidence": 0.95
},
"boxes_xyxy": [
[
278.00640869140625,
171.0072021484375,
330.0191955566406,
307.0115966796875
]
],
"sam_predicted_iou": [
0.9296875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6414.png",
"routing_mask_path": "masks/IMG_6414_routing.png",
"raw_mask_fraction": 0.01731124548584866,
"routing_mask_fraction": 0.02647602250776854
}
transient_person · 1 semantic box(es) · raw 0.26% · route 1.35%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6415",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6415",
"boxes_norm_xyxy": [
[
0.7381,
0.127,
0.8452,
0.3968
]
],
"description": "右上方被喷泉遮挡的行人及背包",
"confidence": 0.87
},
"boxes_xyxy": [
[
372.0024108886719,
48.00600051879883,
425.9808044433594,
149.9904022216797
]
],
"sam_predicted_iou": [
0.76953125
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6415.png",
"routing_mask_path": "masks/IMG_6415_routing.png",
"raw_mask_fraction": 0.002551020408163265,
"routing_mask_fraction": 0.013489963886789283
}
transient_person · 1 semantic box(es) · raw 0.82% · route 1.36%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6416",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6416",
"boxes_norm_xyxy": [
[
0.6706,
0.0714,
0.7778,
0.254
]
],
"description": "喷泉后方远景行人及背包",
"confidence": 0.86
},
"boxes_xyxy": [
[
337.9823913574219,
26.989200592041016,
392.0111999511719,
96.01200103759766
]
],
"sam_predicted_iou": [
0.8046875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6416.png",
"routing_mask_path": "masks/IMG_6416_routing.png",
"raw_mask_fraction": 0.008246199714453683,
"routing_mask_fraction": 0.013579197110943143
}
transient_person · 2 semantic box(es) · raw 1.33% · route 2.32%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6417",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6417",
"boxes_norm_xyxy": [
[
0.4365,
0.4127,
0.5417,
0.6111
],
[
0.881,
0.4048,
0.9286,
0.5026
]
],
"description": "喷泉后方主要行人及手提袋;右侧棚下另有小行人",
"confidence": 0.86
},
"boxes_xyxy": [
[
219.99600219726562,
156.00059509277344,
273.0168151855469,
230.9958038330078
],
[
444.02398681640625,
153.014404296875,
468.014404296875,
189.98280334472656
]
],
"sam_predicted_iou": [
0.90234375,
0.61328125
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6417.png",
"routing_mask_path": "masks/IMG_6417_routing.png",
"raw_mask_fraction": 0.013264256319811875,
"routing_mask_fraction": 0.02324787939867305
}
transient_person · 2 semantic box(es) · raw 1.59% · route 2.65%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6418",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6418",
"boxes_norm_xyxy": [
[
0.3373,
0.5582,
0.4563,
0.8492
],
[
0.881,
0.4762,
0.9365,
0.5608
]
],
"description": "树旁主要行人及黑袋;右侧棚下另有小行人",
"confidence": 0.85
},
"boxes_xyxy": [
[
169.99920654296875,
210.99960327148438,
229.97520446777344,
320.9975891113281
],
[
444.02398681640625,
180.00360107421875,
471.9960021972656,
211.98240661621094
]
],
"sam_predicted_iou": [
0.89453125,
0.69140625
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6418.png",
"routing_mask_path": "masks/IMG_6418_routing.png",
"raw_mask_fraction": 0.015899260938943477,
"routing_mask_fraction": 0.02651801461325271
}
transient_person · 1 semantic box(es) · raw 1.98% · route 3.35%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6419",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6419",
"boxes_norm_xyxy": [
[
0.1369,
0.0741,
0.2877,
0.4392
]
],
"description": "左上方行人及黑色手提袋",
"confidence": 0.98
},
"boxes_xyxy": [
[
68.99759674072266,
28.00979995727539,
145.00079345703125,
166.01759338378906
]
],
"sam_predicted_iou": [
0.92578125
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6419.png",
"routing_mask_path": "masks/IMG_6419_routing.png",
"raw_mask_fraction": 0.019815024775342235,
"routing_mask_fraction": 0.033483455110439236
}
transient_person · 1 semantic box(es) · raw 2.00% · route 3.41%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6420",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6420",
"boxes_norm_xyxy": [
[
0.1964,
0.0635,
0.3452,
0.4524
]
],
"description": "左侧行人及黑色手提袋",
"confidence": 0.98
},
"boxes_xyxy": [
[
98.98560333251953,
24.003000259399414,
173.98080444335938,
171.0072021484375
]
],
"sam_predicted_iou": [
0.921875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6420.png",
"routing_mask_path": "masks/IMG_6420_routing.png",
"raw_mask_fraction": 0.019956748131351305,
"routing_mask_fraction": 0.034071344587217604
}
transient_person · 1 semantic box(es) · raw 1.43% · route 2.96%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6421",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6421",
"boxes_norm_xyxy": [
[
0.2361,
0.4127,
0.369,
0.7751
]
],
"description": "左侧行人,含背包与手提袋",
"confidence": 0.98
},
"boxes_xyxy": [
[
118.99440002441406,
156.00059509277344,
185.9759979248047,
292.98779296875
]
],
"sam_predicted_iou": [
0.828125
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6421.png",
"routing_mask_path": "masks/IMG_6421_routing.png",
"raw_mask_fraction": 0.014282564877802974,
"routing_mask_fraction": 0.02962018140589569
}
transient_person · 2 semantic box(es) · raw 1.88% · route 3.45%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6422",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6422",
"boxes_norm_xyxy": [
[
0.2103,
0.5026,
0.3254,
0.7434
],
[
0.0972,
0.5132,
0.1627,
0.7354
]
],
"description": "喷泉旁主要行人及背包,另含左侧第二名行人",
"confidence": 0.96
},
"boxes_xyxy": [
[
105.99120330810547,
189.98280334472656,
164.00160217285156,
281.00518798828125
],
[
48.988800048828125,
193.98959350585938,
82.00080108642578,
277.981201171875
]
],
"sam_predicted_iou": [
0.9140625,
0.85546875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6422.png",
"routing_mask_path": "masks/IMG_6422_routing.png",
"raw_mask_fraction": 0.018843957336020827,
"routing_mask_fraction": 0.03452275972117242
}
transient_person · 2 semantic box(es) · raw 2.22% · route 3.80%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6423",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6423",
"boxes_norm_xyxy": [
[
0.0992,
0.6111,
0.2341,
1
],
[
0.3571,
0.6429,
0.4127,
0.8598
]
],
"description": "左侧被画面裁切的主要行人及背包/黑袋,另含树后第二人",
"confidence": 0.92
},
"boxes_xyxy": [
[
49.99679946899414,
230.9958038330078,
117.98639678955078,
378.0
],
[
179.9783935546875,
243.01620483398438,
208.00079345703125,
325.00439453125
]
],
"sam_predicted_iou": [
0.90625,
0.71875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6423.png",
"routing_mask_path": "masks/IMG_6423_routing.png",
"raw_mask_fraction": 0.022187578735197784,
"routing_mask_fraction": 0.03803434954228605
}
transient_person · 1 semantic box(es) · raw 2.76% · route 8.64%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6424",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6424",
"boxes_norm_xyxy": [
[
0.2738,
0.1746,
0.4127,
0.5688
]
],
"description": "左侧有清晰行人,含背包和手提袋。",
"confidence": 0.9
},
"boxes_xyxy": [
[
137.9951934814453,
65.9988021850586,
208.00079345703125,
215.0063934326172
]
],
"sam_predicted_iou": [
0.56640625
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6424.png",
"routing_mask_path": "masks/IMG_6424_routing.png",
"raw_mask_fraction": 0.027578315276727976,
"routing_mask_fraction": 0.0863567649281935
}
transient_person · 1 semantic box(es) · raw 1.07% · route 1.70%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6425",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6425",
"boxes_norm_xyxy": [
[
0.3929,
0.336,
0.5079,
0.5899
]
],
"description": "喷泉后方部分遮挡的行人及背包",
"confidence": 0.91
},
"boxes_xyxy": [
[
198.0216064453125,
127.00800323486328,
255.98159790039062,
222.98219299316406
]
],
"sam_predicted_iou": [
0.90625
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6425.png",
"routing_mask_path": "masks/IMG_6425_routing.png",
"raw_mask_fraction": 0.010702737885277569,
"routing_mask_fraction": 0.01699630469471739
}
transient_person · 1 semantic box(es) · raw 0.86% · route 1.58%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6426",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6426",
"boxes_norm_xyxy": [
[
0.5437,
0.5688,
0.6429,
0.7857
]
],
"description": "雕塑后方部分遮挡的行人及背包",
"confidence": 0.89
},
"boxes_xyxy": [
[
274.0248107910156,
215.0063934326172,
324.0216064453125,
296.9945983886719
]
],
"sam_predicted_iou": [
0.87109375
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6426.png",
"routing_mask_path": "masks/IMG_6426_routing.png",
"raw_mask_fraction": 0.00860838162425464,
"routing_mask_fraction": 0.01579952968841858
}
transient_person · 1 semantic box(es) · raw 0.21% · route 0.55%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6427",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6427",
"boxes_norm_xyxy": [
[
0.8929,
0.6032,
0.9345,
0.7249
]
],
"description": "右侧车辆旁远景小行人",
"confidence": 0.63
},
"boxes_xyxy": [
[
450.0216064453125,
228.0095977783203,
470.9880065917969,
274.01220703125
]
],
"sam_predicted_iou": [
0.7734375
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6427.png",
"routing_mask_path": "masks/IMG_6427_routing.png",
"raw_mask_fraction": 0.002062862181909801,
"routing_mask_fraction": 0.0054589737129419665
}
transient_person · 2 semantic box(es) · raw 2.60% · route 4.25%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6428",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6428",
"boxes_norm_xyxy": [
[
0.8095,
0.1032,
0.9603,
0.4683
],
[
0.748,
0.1111,
0.7937,
0.2566
]
],
"description": "右侧主要行人及手提袋,另含其后方小行人",
"confidence": 0.93
},
"boxes_xyxy": [
[
407.9880065917969,
39.00960159301758,
483.9912109375,
177.01739501953125
],
[
376.99200439453125,
41.99580001831055,
400.0248107910156,
96.99479675292969
]
],
"sam_predicted_iou": [
0.93359375,
0.8125
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6428.png",
"routing_mask_path": "masks/IMG_6428_routing.png",
"raw_mask_fraction": 0.02600886033425716,
"routing_mask_fraction": 0.04253275384227765
}
transient_person · 2 semantic box(es) · raw 3.21% · route 5.26%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6429",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6429",
"boxes_norm_xyxy": [
[
0.8135,
0.1455,
0.9802,
0.5529
],
[
0.0734,
0.1825,
0.1548,
0.5159
]
],
"description": "右侧主要行人及背包/黑袋,另含左侧第二人",
"confidence": 0.98
},
"boxes_xyxy": [
[
410.0039978027344,
54.999000549316406,
494.02081298828125,
208.99620056152344
],
[
36.99359893798828,
68.98500061035156,
78.01920318603516,
195.01019287109375
]
],
"sam_predicted_iou": [
0.92578125,
0.8515625
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6429.png",
"routing_mask_path": "masks/IMG_6429_routing.png",
"raw_mask_fraction": 0.0320819685899051,
"routing_mask_fraction": 0.05261610817166373
}
transient_person · 1 semantic box(es) · raw 0.58% · route 1.11%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6430",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6430",
"boxes_norm_xyxy": [
[
0.2262,
0.4021,
0.3036,
0.6164
]
],
"description": "树旁远景行人及背包",
"confidence": 0.88
},
"boxes_xyxy": [
[
114.00479888916016,
151.99380493164062,
153.014404296875,
232.99920654296875
]
],
"sam_predicted_iou": [
0.85546875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6430.png",
"routing_mask_path": "masks/IMG_6430_routing.png",
"raw_mask_fraction": 0.005779163517258755,
"routing_mask_fraction": 0.011148904006046864
}
transient_person · 1 semantic box(es) · raw 0.66% · route 1.30%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6431",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6431",
"boxes_norm_xyxy": [
[
0.4246,
0.5026,
0.5298,
0.7566
]
],
"description": "树与雕塑之间部分遮挡的行人及随身袋",
"confidence": 0.86
},
"boxes_xyxy": [
[
213.99839782714844,
189.98280334472656,
267.0191955566406,
285.99481201171875
]
],
"sam_predicted_iou": [
0.89453125
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6431.png",
"routing_mask_path": "masks/IMG_6431_routing.png",
"raw_mask_fraction": 0.006619005626942135,
"routing_mask_fraction": 0.013017552700092383
}
transient_person · 3 semantic box(es) · raw 2.53% · route 3.95%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6432",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6432",
"boxes_norm_xyxy": [
[
0,
0.3519,
0.0933,
0.6905
],
[
0.5615,
0.3386,
0.619,
0.5265
],
[
0.6468,
0.336,
0.7024,
0.5397
]
],
"description": "左缘被裁切的行人及背包,另含道路旁两名远景行人",
"confidence": 0.92
},
"boxes_xyxy": [
[
0.0,
133.01820373535156,
47.02320098876953,
261.0090026855469
],
[
282.9960021972656,
127.99079895019531,
311.97601318359375,
199.01699829101562
],
[
325.9872131347656,
127.00800323486328,
354.0096130371094,
204.00660705566406
]
],
"sam_predicted_iou": [
0.91796875,
0.78515625,
0.84765625
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6432.png",
"routing_mask_path": "masks/IMG_6432_routing.png",
"raw_mask_fraction": 0.02530549256739733,
"routing_mask_fraction": 0.0394883261946754
}
transient_person · 2 semantic box(es) · raw 2.80% · route 4.32%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6433",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6433",
"boxes_norm_xyxy": [
[
0.123,
0.2857,
0.2619,
0.6323
],
[
0.8294,
0.3175,
0.9147,
0.5476
]
],
"description": "左侧主要行人及背包/手提袋,另含右侧第二人",
"confidence": 0.97
},
"boxes_xyxy": [
[
61.992000579833984,
107.99459838867188,
131.9976043701172,
239.0093994140625
],
[
418.0176086425781,
120.01499938964844,
461.0087890625,
206.9927978515625
]
],
"sam_predicted_iou": [
0.91796875,
0.84765625
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6433.png",
"routing_mask_path": "masks/IMG_6433_routing.png",
"raw_mask_fraction": 0.02802448139749727,
"routing_mask_fraction": 0.04319412950365331
}
transient_person · 2 semantic box(es) · raw 3.73% · route 5.81%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6434",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6434",
"boxes_norm_xyxy": [
[
0.6171,
0.2222,
0.7698,
0.6085
],
[
0.9067,
0.2831,
0.9782,
0.5238
]
],
"description": "树前主要行人及背包/手提袋,另含右侧第二人",
"confidence": 0.97
},
"boxes_xyxy": [
[
311.0184020996094,
83.9916000366211,
387.97918701171875,
230.01300048828125
],
[
456.976806640625,
107.01180267333984,
493.0127868652344,
197.99639892578125
]
],
"sam_predicted_iou": [
0.8515625,
0.890625
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6434.png",
"routing_mask_path": "masks/IMG_6434_routing.png",
"raw_mask_fraction": 0.03731523473586966,
"routing_mask_fraction": 0.05806458385823465
}
transient_person · 1 semantic box(es) · raw 0.80% · route 1.55%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6435",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6435",
"boxes_norm_xyxy": [
[
0.9345,
0.1905,
1,
0.5582
]
],
"description": "右缘有被画面裁切但清晰可辨的行人。",
"confidence": 0.9
},
"boxes_xyxy": [
[
470.9880065917969,
72.00900268554688,
504.0,
210.99960327148438
]
],
"sam_predicted_iou": [
0.6328125
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6435.png",
"routing_mask_path": "masks/IMG_6435_routing.png",
"raw_mask_fraction": 0.008025741160661796,
"routing_mask_fraction": 0.015453094818174183
}
transient_person · 2 semantic box(es) · raw 2.94% · route 4.59%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6437",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6437",
"boxes_norm_xyxy": [
[
0.754,
0,
0.9246,
0.4101
],
[
0.4306,
0.0503,
0.5238,
0.2566
]
],
"description": "右上方被裁切的主要行人及背包,另含道路旁第二人",
"confidence": 0.93
},
"boxes_xyxy": [
[
380.0159912109375,
0.0,
465.9984130859375,
155.01780700683594
],
[
217.02239990234375,
19.013399124145508,
263.9952087402344,
96.99479675292969
]
],
"sam_predicted_iou": [
0.86328125,
0.8515625
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6437.png",
"routing_mask_path": "masks/IMG_6437_routing.png",
"raw_mask_fraction": 0.02943121693121693,
"routing_mask_fraction": 0.045949861426051904
}
transient_person · 2 semantic box(es) · raw 1.61% · route 2.43%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6438",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6438",
"boxes_norm_xyxy": [
[
0.5595,
0,
0.6845,
0.1878
],
[
0.2738,
0,
0.3353,
0.127
]
],
"description": "上缘被裁切的主要行人及背包,另含左上远景行人",
"confidence": 0.87
},
"boxes_xyxy": [
[
281.9880065917969,
0.0,
344.9880065917969,
70.9884033203125
],
[
137.9951934814453,
0.0,
168.99119567871094,
48.00600051879883
]
],
"sam_predicted_iou": [
0.88671875,
0.87890625
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6438.png",
"routing_mask_path": "masks/IMG_6438_routing.png",
"raw_mask_fraction": 0.016061980347694634,
"routing_mask_fraction": 0.024250440917107582
}
transient_person · 1 semantic box(es) · raw 1.51% · route 2.27%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6439",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6439",
"boxes_norm_xyxy": [
[
0.502,
0.3228,
0.6151,
0.6111
]
],
"description": "喷泉后方行人及黑色手提袋",
"confidence": 0.97
},
"boxes_xyxy": [
[
253.00799560546875,
122.01840209960938,
310.0104064941406,
230.9958038330078
]
],
"sam_predicted_iou": [
0.91796875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6439.png",
"routing_mask_path": "masks/IMG_6439_routing.png",
"raw_mask_fraction": 0.015122406987486353,
"routing_mask_fraction": 0.02272822709330646
}
transient_person · 1 semantic box(es) · raw 1.63% · route 2.40%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6440",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6440",
"boxes_norm_xyxy": [
[
0.4484,
0.4365,
0.5575,
0.7407
]
],
"description": "喷泉后方行人及背包/手提袋",
"confidence": 0.96
},
"boxes_xyxy": [
[
225.9936065673828,
164.9969940185547,
280.9800109863281,
279.9845886230469
]
],
"sam_predicted_iou": [
0.8984375
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6440.png",
"routing_mask_path": "masks/IMG_6440_routing.png",
"raw_mask_fraction": 0.01628768791467204,
"routing_mask_fraction": 0.023987990257831528
}
transient_person · 1 semantic box(es) · raw 1.89% · route 2.78%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6441",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6441",
"boxes_norm_xyxy": [
[
0.5774,
0.4101,
0.7202,
0.7275
]
],
"description": "喷泉后方行人及黑色手提袋",
"confidence": 0.98
},
"boxes_xyxy": [
[
291.0096130371094,
155.01780700683594,
362.9808044433594,
274.9949951171875
]
],
"sam_predicted_iou": [
0.921875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6441.png",
"routing_mask_path": "masks/IMG_6441_routing.png",
"raw_mask_fraction": 0.01890169648106156,
"routing_mask_fraction": 0.027814520870076426
}
transient_person · 1 semantic box(es) · raw 2.00% · route 2.89%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6442",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6442",
"boxes_norm_xyxy": [
[
0.6488,
0.1164,
0.7758,
0.4233
]
],
"description": "喷泉后方有清晰行人及手提袋。",
"confidence": 0.9
},
"boxes_xyxy": [
[
326.9952087402344,
43.99919891357422,
391.0032043457031,
160.0074005126953
]
],
"sam_predicted_iou": [
0.91015625
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6442.png",
"routing_mask_path": "masks/IMG_6442_routing.png",
"raw_mask_fraction": 0.0200302343159486,
"routing_mask_fraction": 0.028895817586293778
}
transient_person · 1 semantic box(es) · raw 2.95% · route 3.82%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6443",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6443",
"boxes_norm_xyxy": [
[
0.7758,
0,
0.9643,
0.2672
]
],
"description": "右上缘被裁切的行人及手提袋",
"confidence": 0.9
},
"boxes_xyxy": [
[
391.0032043457031,
0.0,
486.0072021484375,
101.00160217285156
]
],
"sam_predicted_iou": [
0.9375
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6443.png",
"routing_mask_path": "masks/IMG_6443_routing.png",
"raw_mask_fraction": 0.02953094818174183,
"routing_mask_fraction": 0.03818132191148064
}
no_prominent_transient · 0 semantic box(es) · raw 0.00% · route 0.00%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6444",
"cause": "no_prominent_transient",
"agent_record": null,
"boxes_xyxy": [],
"sam_predicted_iou": [],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6444.png",
"routing_mask_path": "masks/IMG_6444_routing.png",
"raw_mask_fraction": 0.0,
"routing_mask_fraction": 0.0
}
transient_person · 1 semantic box(es) · raw 0.57% · route 1.12%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6445",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6445",
"boxes_norm_xyxy": [
[
0.5238,
0.1508,
0.6171,
0.3862
]
],
"description": "道路对面远景行人",
"confidence": 0.88
},
"boxes_xyxy": [
[
263.9952087402344,
57.00239944458008,
311.0184020996094,
145.9835968017578
]
],
"sam_predicted_iou": [
0.8515625
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6445.png",
"routing_mask_path": "masks/IMG_6445_routing.png",
"raw_mask_fraction": 0.005700428319475938,
"routing_mask_fraction": 0.011222390190644159
}
no_prominent_transient · 0 semantic box(es) · raw 0.00% · route 0.00%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6446",
"cause": "no_prominent_transient",
"agent_record": null,
"boxes_xyxy": [],
"sam_predicted_iou": [],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6446.png",
"routing_mask_path": "masks/IMG_6446_routing.png",
"raw_mask_fraction": 0.0,
"routing_mask_fraction": 0.0
}
transient_person · 1 semantic box(es) · raw 1.69% · route 2.77%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6447",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6447",
"boxes_norm_xyxy": [
[
0.9365,
0.1825,
1,
0.7989
]
],
"description": "右缘被严重裁切的行人及黑色随身袋",
"confidence": 0.81
},
"boxes_xyxy": [
[
471.9960021972656,
68.98500061035156,
504.0,
301.98419189453125
]
],
"sam_predicted_iou": [
0.91796875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6447.png",
"routing_mask_path": "masks/IMG_6447_routing.png",
"raw_mask_fraction": 0.01693856554967666,
"routing_mask_fraction": 0.02774628369866465
}
transient_person · 1 semantic box(es) · raw 2.51% · route 3.83%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6448",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6448",
"boxes_norm_xyxy": [
[
0.756,
0.1429,
0.8869,
0.5767
]
],
"description": "One pedestrian at right, including worn backpack.",
"confidence": 0.98
},
"boxes_xyxy": [
[
381.02398681640625,
54.01620101928711,
446.9975891113281,
217.9925994873047
]
],
"sam_predicted_iou": [
0.91796875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6448.png",
"routing_mask_path": "masks/IMG_6448_routing.png",
"raw_mask_fraction": 0.025106030066347526,
"routing_mask_fraction": 0.03830204921474763
}
transient_person · 1 semantic box(es) · raw 3.00% · route 4.50%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6449",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6449",
"boxes_norm_xyxy": [
[
0.7718,
0.0,
0.9385,
0.4286
]
],
"description": "Top-clipped pedestrian at right, including black carried/worn bag.",
"confidence": 0.96
},
"boxes_xyxy": [
[
388.9872131347656,
0.0,
473.0039978027344,
162.01080322265625
]
],
"sam_predicted_iou": [
0.9140625
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6449.png",
"routing_mask_path": "masks/IMG_6449_routing.png",
"raw_mask_fraction": 0.02995086923658352,
"routing_mask_fraction": 0.04503128411858571
}
transient_person · 1 semantic box(es) · raw 2.39% · route 3.08%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6450",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6450",
"boxes_norm_xyxy": [
[
0.9107,
0.0,
1.0,
0.4286
]
],
"description": "Severely right-clipped pedestrian.",
"confidence": 0.96
},
"boxes_xyxy": [
[
458.9927978515625,
0.0,
504.0,
162.01080322265625
]
],
"sam_predicted_iou": [
0.94921875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6450.png",
"routing_mask_path": "masks/IMG_6450_routing.png",
"raw_mask_fraction": 0.023883009994121105,
"routing_mask_fraction": 0.030764466280339298
}
no_prominent_transient · 0 semantic box(es) · raw 0.00% · route 0.00%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6451",
"cause": "no_prominent_transient",
"agent_record": null,
"boxes_xyxy": [],
"sam_predicted_iou": [],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6451.png",
"routing_mask_path": "masks/IMG_6451_routing.png",
"raw_mask_fraction": 0.0,
"routing_mask_fraction": 0.0
}
transient_person · 1 semantic box(es) · raw 4.55% · route 6.29%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6452",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6452",
"boxes_norm_xyxy": [
[
0.748,
0.0,
0.9544,
0.4735
]
],
"description": "Top-clipped pedestrian and backpack at right.",
"confidence": 0.98
},
"boxes_xyxy": [
[
376.99200439453125,
0.0,
481.0176086425781,
178.98300170898438
]
],
"sam_predicted_iou": [
0.91796875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6452.png",
"routing_mask_path": "masks/IMG_6452_routing.png",
"raw_mask_fraction": 0.04551419333165365,
"routing_mask_fraction": 0.06291467204165617
}
transient_person · 1 semantic box(es) · raw 2.15% · route 3.65%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6453",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6453",
"boxes_norm_xyxy": [
[
0.7044,
0.2593,
0.8313,
0.6984
]
],
"description": "One pedestrian walking away, including backpack.",
"confidence": 0.98
},
"boxes_xyxy": [
[
355.0176086425781,
98.0154037475586,
418.9751892089844,
263.9952087402344
]
],
"sam_predicted_iou": [
0.90234375
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6453.png",
"routing_mask_path": "masks/IMG_6453_routing.png",
"raw_mask_fraction": 0.021505207021080035,
"routing_mask_fraction": 0.03648589065255732
}
transient_person · 1 semantic box(es) · raw 2.12% · route 3.55%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6454",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6454",
"boxes_norm_xyxy": [
[
0.6825,
0.4312,
0.8274,
0.828
]
],
"description": "One pedestrian, including black bag at left side.",
"confidence": 0.97
},
"boxes_xyxy": [
[
343.9800109863281,
162.9936065673828,
417.0096130371094,
312.9840087890625
]
],
"sam_predicted_iou": [
0.89453125
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6454.png",
"routing_mask_path": "masks/IMG_6454_routing.png",
"raw_mask_fraction": 0.021158772150835642,
"routing_mask_fraction": 0.03551482321323591
}
transient_person · 1 semantic box(es) · raw 5.94% · route 7.90%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6455",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6455",
"boxes_norm_xyxy": [
[
0.627,
0.0,
0.8948,
0.6058
]
],
"description": "Large top-clipped pedestrian with backpack and carried black bag.",
"confidence": 0.99
},
"boxes_xyxy": [
[
316.00799560546875,
0.0,
450.97918701171875,
228.99240112304688
]
],
"sam_predicted_iou": [
0.9296875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6455.png",
"routing_mask_path": "masks/IMG_6455_routing.png",
"raw_mask_fraction": 0.05940308222054254,
"routing_mask_fraction": 0.07901864449483498
}
transient_person · 1 semantic box(es) · raw 3.02% · route 5.11%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6456",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6456",
"boxes_norm_xyxy": [
[
0.619,
0.3333,
0.7738,
0.8228
]
],
"description": "One pedestrian walking away, including backpack and thin carried item.",
"confidence": 0.98
},
"boxes_xyxy": [
[
311.97601318359375,
125.98739624023438,
389.9952087402344,
311.0184020996094
]
],
"sam_predicted_iou": [
0.9140625
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6456.png",
"routing_mask_path": "masks/IMG_6456_routing.png",
"raw_mask_fraction": 0.030239564961787185,
"routing_mask_fraction": 0.05108339632149156
}
transient_person · 1 semantic box(es) · raw 3.26% · route 4.88%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6457",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6457",
"boxes_norm_xyxy": [
[
0.5595,
0.5026,
0.7341,
0.9497
]
],
"description": "One pedestrian facing camera, including backpack and black hand bag.",
"confidence": 0.98
},
"boxes_xyxy": [
[
281.9880065917969,
189.98280334472656,
369.98638916015625,
358.9866027832031
]
],
"sam_predicted_iou": [
0.92578125
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6457.png",
"routing_mask_path": "masks/IMG_6457_routing.png",
"raw_mask_fraction": 0.03261211892164273,
"routing_mask_fraction": 0.048752834467120185
}
transient_person · 1 semantic box(es) · raw 3.62% · route 5.01%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6458",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6458",
"boxes_norm_xyxy": [
[
0.7401,
0.5106,
0.8909,
1.0
]
],
"description": "Bottom-clipped pedestrian, including backpack and bundled black bag.",
"confidence": 0.98
},
"boxes_xyxy": [
[
373.0104064941406,
193.00680541992188,
449.01361083984375,
378.0
]
],
"sam_predicted_iou": [
0.91796875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6458.png",
"routing_mask_path": "masks/IMG_6458_routing.png",
"raw_mask_fraction": 0.036212941966910224,
"routing_mask_fraction": 0.05010707986898463
}
transient_person · 1 semantic box(es) · raw 7.62% · route 11.17%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6459",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6459",
"boxes_norm_xyxy": [
[
0.633,
0.0926,
0.881,
0.9233
]
],
"description": "One prominent pedestrian with backpack and large black bag across torso.",
"confidence": 0.99
},
"boxes_xyxy": [
[
319.0320129394531,
35.00279998779297,
444.02398681640625,
349.00738525390625
]
],
"sam_predicted_iou": [
0.94921875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6459.png",
"routing_mask_path": "masks/IMG_6459_routing.png",
"raw_mask_fraction": 0.07618417737465356,
"routing_mask_fraction": 0.11168325354833292
}
transient_person · 1 semantic box(es) · raw 10.89% · route 13.43%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6461",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6461",
"boxes_norm_xyxy": [
[
0.6885,
0.2222,
0.9306,
1.0
]
],
"description": "Bottom-clipped older pedestrian walking away, including carried paper.",
"confidence": 0.98
},
"boxes_xyxy": [
[
347.0039978027344,
83.9916000366211,
469.02239990234375,
378.0
]
],
"sam_predicted_iou": [
0.96484375
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6461.png",
"routing_mask_path": "masks/IMG_6461_routing.png",
"raw_mask_fraction": 0.10885403544133702,
"routing_mask_fraction": 0.13429600235155792
}
transient_person · 2 semantic box(es) · raw 22.46% · route 26.33%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6462",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6462",
"boxes_norm_xyxy": [
[
0.0,
0.2381,
0.4623,
1.0
],
[
0.7798,
0.3624,
0.9087,
0.8042
]
],
"description": "Large foreground pedestrian with backpack plus one background older pedestrian.",
"confidence": 0.97
},
"boxes_xyxy": [
[
0.0,
90.00180053710938,
232.99920654296875,
378.0
],
[
393.0191955566406,
136.98719787597656,
457.98480224609375,
303.98760986328125
]
],
"sam_predicted_iou": [
0.95703125,
0.953125
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6462.png",
"routing_mask_path": "masks/IMG_6462_routing.png",
"raw_mask_fraction": 0.22461577223481985,
"routing_mask_fraction": 0.26328525237255396
}
transient_person · 1 semantic box(es) · raw 1.88% · route 2.97%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6463",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6463",
"boxes_norm_xyxy": [
[
0.879,
0.4762,
1,
0.8757
]
],
"description": "右侧有清晰背向行走的人,身体部分贴近画面边缘。",
"confidence": 0.9
},
"boxes_xyxy": [
[
443.0159912109375,
180.00360107421875,
504.0,
331.01458740234375
]
],
"sam_predicted_iou": [
0.93359375
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6463.png",
"routing_mask_path": "masks/IMG_6463_routing.png",
"raw_mask_fraction": 0.018754724111866967,
"routing_mask_fraction": 0.02970416561686403
}
no_prominent_transient · 0 semantic box(es) · raw 0.00% · route 0.00%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6464",
"cause": "no_prominent_transient",
"agent_record": null,
"boxes_xyxy": [],
"sam_predicted_iou": [],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6464.png",
"routing_mask_path": "masks/IMG_6464_routing.png",
"raw_mask_fraction": 0.0,
"routing_mask_fraction": 0.0
}
no_prominent_transient · 0 semantic box(es) · raw 0.00% · route 0.00%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6465",
"cause": "no_prominent_transient",
"agent_record": null,
"boxes_xyxy": [],
"sam_predicted_iou": [],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6465.png",
"routing_mask_path": "masks/IMG_6465_routing.png",
"raw_mask_fraction": 0.0,
"routing_mask_fraction": 0.0
}
transient_person · 1 semantic box(es) · raw 1.46% · route 2.08%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6466",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6466",
"boxes_norm_xyxy": [
[
0.0,
0.0,
0.1012,
0.2751
]
],
"description": "Small top-left clipped portion of pedestrian and black bag.",
"confidence": 0.91
},
"boxes_xyxy": [
[
0.0,
0.0,
51.004798889160156,
103.98780059814453
]
],
"sam_predicted_iou": [
0.95703125
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6466.png",
"routing_mask_path": "masks/IMG_6466_routing.png",
"raw_mask_fraction": 0.014613252708490804,
"routing_mask_fraction": 0.02081758629377677
}
no_prominent_transient · 0 semantic box(es) · raw 0.00% · route 0.00%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6467",
"cause": "no_prominent_transient",
"agent_record": null,
"boxes_xyxy": [],
"sam_predicted_iou": [],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6467.png",
"routing_mask_path": "masks/IMG_6467_routing.png",
"raw_mask_fraction": 0.0,
"routing_mask_fraction": 0.0
}
transient_person · 1 semantic box(es) · raw 14.59% · route 18.38%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6468",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6468",
"boxes_norm_xyxy": [
[
0.1151,
0.082,
0.4782,
1.0
]
],
"description": "Large foreground pedestrian, including backpack and carried black bag.",
"confidence": 0.99
},
"boxes_xyxy": [
[
58.010398864746094,
30.996000289916992,
241.01280212402344,
378.0
]
],
"sam_predicted_iou": [
0.9453125
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6468.png",
"routing_mask_path": "masks/IMG_6468_routing.png",
"raw_mask_fraction": 0.14590157050474512,
"routing_mask_fraction": 0.18379944570420761
}
transient_person · 1 semantic box(es) · raw 13.48% · route 15.38%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6469",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6469",
"boxes_norm_xyxy": [
[
0.5099,
0.3201,
0.8373,
1.0
]
],
"description": "Bottom-clipped pedestrian at right, including large backpack.",
"confidence": 0.99
},
"boxes_xyxy": [
[
256.9895935058594,
120.997802734375,
421.99920654296875,
378.0
]
],
"sam_predicted_iou": [
0.9609375
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6469.png",
"routing_mask_path": "masks/IMG_6469_routing.png",
"raw_mask_fraction": 0.13482090367011001,
"routing_mask_fraction": 0.15380658436213993
}
transient_person · 1 semantic box(es) · raw 16.81% · route 18.82%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6470",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6470",
"boxes_norm_xyxy": [
[
0.7123,
0.0,
1.0,
1.0
]
],
"description": "Right- and bottom-clipped pedestrian with backpack and black hand bag.",
"confidence": 0.99
},
"boxes_xyxy": [
[
358.99920654296875,
0.0,
504.0,
378.0
]
],
"sam_predicted_iou": [
0.94921875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6470.png",
"routing_mask_path": "masks/IMG_6470_routing.png",
"raw_mask_fraction": 0.16813114134542706,
"routing_mask_fraction": 0.18823486184597296
}
transient_person · 1 semantic box(es) · raw 10.49% · route 14.30%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6471",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6471",
"boxes_norm_xyxy": [
[
0.0496,
0.1693,
0.2877,
1.0
]
],
"description": "Bottom-clipped pedestrian at left, including backpack.",
"confidence": 0.99
},
"boxes_xyxy": [
[
24.99839973449707,
63.995399475097656,
145.00079345703125,
378.0
]
],
"sam_predicted_iou": [
0.96484375
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6471.png",
"routing_mask_path": "masks/IMG_6471_routing.png",
"raw_mask_fraction": 0.10486478542034097,
"routing_mask_fraction": 0.14297787016040983
}
transient_person · 1 semantic box(es) · raw 1.97% · route 2.50%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6472",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6472",
"boxes_norm_xyxy": [
[
0.0,
0.5265,
0.0873,
0.8492
]
],
"description": "Left-clipped pedestrian fragment dominated by backpack and sleeve.",
"confidence": 0.9
},
"boxes_xyxy": [
[
0.0,
199.01699829101562,
43.99919891357422,
320.9975891113281
]
],
"sam_predicted_iou": [
0.97265625
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6472.png",
"routing_mask_path": "masks/IMG_6472_routing.png",
"raw_mask_fraction": 0.01974153859074494,
"routing_mask_fraction": 0.0249748047367095
}
transient_person · 1 semantic box(es) · raw 3.37% · route 4.22%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6473",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6473",
"boxes_norm_xyxy": [
[
0.0,
0.3836,
0.1091,
1.0
]
],
"description": "Left- and bottom-clipped pedestrian.",
"confidence": 0.96
},
"boxes_xyxy": [
[
0.0,
145.00079345703125,
54.98640060424805,
378.0
]
],
"sam_predicted_iou": [
0.96484375
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6473.png",
"routing_mask_path": "masks/IMG_6473_routing.png",
"raw_mask_fraction": 0.033651423532375914,
"routing_mask_fraction": 0.04220206601158982
}
transient_person · 1 semantic box(es) · raw 20.11% · route 23.00%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6474",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6474",
"boxes_norm_xyxy": [
[
0.0159,
0.0,
0.377,
1.0
]
],
"description": "Large clipped pedestrian with backpack and carried black bag.",
"confidence": 0.99
},
"boxes_xyxy": [
[
8.01360034942627,
0.0,
190.00799560546875,
378.0
]
],
"sam_predicted_iou": [
0.94140625
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6474.png",
"routing_mask_path": "masks/IMG_6474_routing.png",
"raw_mask_fraction": 0.2010686990845721,
"routing_mask_fraction": 0.23001700680272108
}
transient_person · 1 semantic box(es) · raw 15.97% · route 20.33%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6475",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6475",
"boxes_norm_xyxy": [
[
0.1508,
0.0,
0.6429,
0.8254
]
],
"description": "Top-clipped walking pedestrian, including backpack and large carried bag.",
"confidence": 0.99
},
"boxes_xyxy": [
[
76.0031967163086,
0.0,
324.0216064453125,
312.0011901855469
]
],
"sam_predicted_iou": [
0.9453125
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6475.png",
"routing_mask_path": "masks/IMG_6475_routing.png",
"raw_mask_fraction": 0.15965398505081044,
"routing_mask_fraction": 0.20334677080708827
}
no_prominent_transient · 0 semantic box(es) · raw 0.00% · route 0.00%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6476",
"cause": "no_prominent_transient",
"agent_record": null,
"boxes_xyxy": [],
"sam_predicted_iou": [],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6476.png",
"routing_mask_path": "masks/IMG_6476_routing.png",
"raw_mask_fraction": 0.0,
"routing_mask_fraction": 0.0
}
no_prominent_transient · 0 semantic box(es) · raw 0.00% · route 0.00%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6477",
"cause": "no_prominent_transient",
"agent_record": {
"frame_id": "IMG_6477",
"boxes_norm_xyxy": [],
"description": "No transient person; only static fountain, sculpture, buildings, and street fixtures.",
"confidence": 0.99
},
"boxes_xyxy": [],
"sam_predicted_iou": [],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6477.png",
"routing_mask_path": "masks/IMG_6477_routing.png",
"raw_mask_fraction": 0.0,
"routing_mask_fraction": 0.0
}
no_prominent_transient · 0 semantic box(es) · raw 0.00% · route 0.00%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6478",
"cause": "no_prominent_transient",
"agent_record": null,
"boxes_xyxy": [],
"sam_predicted_iou": [],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6478.png",
"routing_mask_path": "masks/IMG_6478_routing.png",
"raw_mask_fraction": 0.0,
"routing_mask_fraction": 0.0
}
no_prominent_transient · 0 semantic box(es) · raw 0.00% · route 0.00%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6479",
"cause": "no_prominent_transient",
"agent_record": {
"frame_id": "IMG_6479",
"boxes_norm_xyxy": [],
"description": "No transient person; close view of static fountain and sculpture.",
"confidence": 0.99
},
"boxes_xyxy": [],
"sam_predicted_iou": [],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6479.png",
"routing_mask_path": "masks/IMG_6479_routing.png",
"raw_mask_fraction": 0.0,
"routing_mask_fraction": 0.0
}
no_prominent_transient · 0 semantic box(es) · raw 0.00% · route 0.00%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6480",
"cause": "no_prominent_transient",
"agent_record": null,
"boxes_xyxy": [],
"sam_predicted_iou": [],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6480.png",
"routing_mask_path": "masks/IMG_6480_routing.png",
"raw_mask_fraction": 0.0,
"routing_mask_fraction": 0.0
}
transient_person · 1 semantic box(es) · raw 1.44% · route 2.03%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6481",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6481",
"boxes_norm_xyxy": [
[
0.6687,
0.0,
0.869,
0.1376
]
],
"description": "Severely top-clipped pedestrian with backpack/black bag visible above fountain.",
"confidence": 0.88
},
"boxes_xyxy": [
[
337.0248107910156,
0.0,
437.97601318359375,
52.01279830932617
]
],
"sam_predicted_iou": [
0.875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6481.png",
"routing_mask_path": "masks/IMG_6481_routing.png",
"raw_mask_fraction": 0.014350802049214748,
"routing_mask_fraction": 0.020271688922482572
}
transient_person · 1 semantic box(es) · raw 1.87% · route 2.70%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6482",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6482",
"boxes_norm_xyxy": [
[
0.5774,
0.1878,
0.7083,
0.4868
]
],
"description": "One background pedestrian, including backpack and black hand bag.",
"confidence": 0.98
},
"boxes_xyxy": [
[
291.0096130371094,
70.9884033203125,
356.9831848144531,
184.01040649414062
]
],
"sam_predicted_iou": [
0.9296875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6482.png",
"routing_mask_path": "masks/IMG_6482_routing.png",
"raw_mask_fraction": 0.018686486940455195,
"routing_mask_fraction": 0.027021919879062738
}
transient_person · 1 semantic box(es) · raw 1.83% · route 2.80%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6483",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6483",
"boxes_norm_xyxy": [
[
0.3651,
0.4153,
0.504,
0.7249
]
],
"description": "One pedestrian near road, including backpack and hand bag.",
"confidence": 0.98
},
"boxes_xyxy": [
[
184.01040649414062,
156.9833984375,
254.01600646972656,
274.01220703125
]
],
"sam_predicted_iou": [
0.82421875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6483.png",
"routing_mask_path": "masks/IMG_6483_routing.png",
"raw_mask_fraction": 0.018277063911984547,
"routing_mask_fraction": 0.027998236331569663
}
transient_person · 1 semantic box(es) · raw 2.42% · route 3.67%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6484",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6484",
"boxes_norm_xyxy": [
[
0.119,
0.4444,
0.2877,
0.8016
]
],
"description": "One pedestrian at left, including backpack and black hand bag.",
"confidence": 0.98
},
"boxes_xyxy": [
[
59.97600173950195,
167.9832000732422,
145.00079345703125,
303.0047912597656
]
],
"sam_predicted_iou": [
0.93359375
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6484.png",
"routing_mask_path": "masks/IMG_6484_routing.png",
"raw_mask_fraction": 0.0242294448643655,
"routing_mask_fraction": 0.03672734525909129
}
transient_person · 1 semantic box(es) · raw 1.75% · route 2.58%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6485",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6485",
"boxes_norm_xyxy": [
[
0.2401,
0.2302,
0.3353,
0.5265
]
],
"description": "One background pedestrian, including backpack and black hand bag.",
"confidence": 0.97
},
"boxes_xyxy": [
[
121.0103988647461,
87.0156021118164,
168.99119567871094,
199.01699829101562
]
],
"sam_predicted_iou": [
0.91015625
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6485.png",
"routing_mask_path": "masks/IMG_6485_routing.png",
"raw_mask_fraction": 0.017452968841857732,
"routing_mask_fraction": 0.025798899806836313
}
transient_person · 1 semantic box(es) · raw 1.45% · route 2.24%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6486",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6486",
"boxes_norm_xyxy": [
[
0.4365,
0.0397,
0.5397,
0.3148
]
],
"description": "Top-near pedestrian, including backpack and black hand bag.",
"confidence": 0.97
},
"boxes_xyxy": [
[
219.99600219726562,
15.006600379943848,
272.0087890625,
118.99440002441406
]
],
"sam_predicted_iou": [
0.921875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6486.png",
"routing_mask_path": "masks/IMG_6486_routing.png",
"raw_mask_fraction": 0.014545015537079029,
"routing_mask_fraction": 0.02240278827580415
}
transient_person · 1 semantic box(es) · raw 0.45% · route 0.83%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6487",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6487",
"boxes_norm_xyxy": [
[
0,
0,
0.0595,
0.1349
]
],
"description": "左上角有被画面裁切但可明确识别的近景行人双腿。",
"confidence": 0.9
},
"boxes_xyxy": [
[
0.0,
0.0,
29.988000869750977,
50.9921989440918
]
],
"sam_predicted_iou": [
0.92578125
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6487.png",
"routing_mask_path": "masks/IMG_6487_routing.png",
"raw_mask_fraction": 0.004482657260435038,
"routing_mask_fraction": 0.008267195767195767
}
no_prominent_transient · 0 semantic box(es) · raw 0.00% · route 0.00%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6488",
"cause": "no_prominent_transient",
"agent_record": null,
"boxes_xyxy": [],
"sam_predicted_iou": [],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6488.png",
"routing_mask_path": "masks/IMG_6488_routing.png",
"raw_mask_fraction": 0.0,
"routing_mask_fraction": 0.0
}
transient_person · 3 semantic box(es) · raw 3.77% · route 5.99%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6489",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6489",
"boxes_norm_xyxy": [
[
0.1171,
0.0,
0.2877,
0.3492
],
[
0.0893,
0.0317,
0.131,
0.1693
],
[
0.3532,
0.0,
0.3968,
0.127
]
],
"description": "One top-clipped foreground pedestrian with bag and two small background pedestrians.",
"confidence": 0.82
},
"boxes_xyxy": [
[
59.01839828491211,
0.0,
145.00079345703125,
131.9976043701172
],
[
45.007198333740234,
11.982600212097168,
66.02400207519531,
63.995399475097656
],
[
178.01280212402344,
0.0,
199.98719787597656,
48.00600051879883
]
],
"sam_predicted_iou": [
0.92578125,
0.890625,
0.5234375
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6489.png",
"routing_mask_path": "masks/IMG_6489_routing.png",
"raw_mask_fraction": 0.03765642059292853,
"routing_mask_fraction": 0.059906987486352564
}
transient_person · 3 semantic box(es) · raw 6.13% · route 8.61%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6490",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6490",
"boxes_norm_xyxy": [
[
0.0278,
0.3333,
0.2361,
0.9444
],
[
0.3948,
0.2831,
0.4385,
0.3995
],
[
0.5992,
0.1614,
0.6329,
0.2302
]
],
"description": "One prominent foreground pedestrian with bag and two background pedestrians.",
"confidence": 0.86
},
"boxes_xyxy": [
[
14.011199951171875,
125.98739624023438,
118.99440002441406,
356.9831848144531
],
[
198.9792022705078,
107.01180267333984,
221.00399780273438,
151.01100158691406
],
[
301.9967956542969,
61.00920104980469,
318.9815979003906,
87.0156021118164
]
],
"sam_predicted_iou": [
0.94921875,
0.8671875,
0.74609375
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6490.png",
"routing_mask_path": "masks/IMG_6490_routing.png",
"raw_mask_fraction": 0.061282228940959096,
"routing_mask_fraction": 0.08613630637440162
}
transient_person · 4 semantic box(es) · raw 4.80% · route 6.83%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6491",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6491",
"boxes_norm_xyxy": [
[
0.1488,
0.6032,
0.2917,
1.0
],
[
0.3135,
0.5608,
0.3611,
0.6878
],
[
0.3948,
0.5635,
0.4345,
0.6614
],
[
0.4841,
0.5106,
0.5337,
0.6111
]
],
"description": "Bottom-clipped foreground pedestrian plus three distinct pedestrians crossing in background.",
"confidence": 0.86
},
"boxes_xyxy": [
[
74.99520111083984,
228.0095977783203,
147.0167999267578,
378.0
],
[
158.00399780273438,
211.98240661621094,
181.99440002441406,
259.9884033203125
],
[
198.9792022705078,
213.0030059814453,
218.98800659179688,
250.0092010498047
],
[
243.9864044189453,
193.00680541992188,
268.98480224609375,
230.9958038330078
]
],
"sam_predicted_iou": [
0.9609375,
0.77734375,
0.73828125,
0.8203125
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6491.png",
"routing_mask_path": "masks/IMG_6491_routing.png",
"raw_mask_fraction": 0.04799172755521962,
"routing_mask_fraction": 0.06832640463592844
}
transient_person · 1 semantic box(es) · raw 0.86% · route 1.32%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6492",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6492",
"boxes_norm_xyxy": [
[
0.3234,
0,
0.4683,
0.0661
]
],
"description": "上缘、喷泉后方露出一名被严重遮挡的行人及深色随身物。",
"confidence": 0.9
},
"boxes_xyxy": [
[
162.9936065673828,
0.0,
236.023193359375,
24.98579978942871
]
],
"sam_predicted_iou": [
0.625
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6492.png",
"routing_mask_path": "masks/IMG_6492_routing.png",
"raw_mask_fraction": 0.008603132611069118,
"routing_mask_fraction": 0.013243260267069791
}
transient_person · 5 semantic box(es) · raw 4.96% · route 8.18%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6493",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6493",
"boxes_norm_xyxy": [
[
0.0734,
0.1693,
0.127,
0.418
],
[
0.1052,
0.1455,
0.1944,
0.4074
],
[
0.2123,
0.1905,
0.2698,
0.3519
],
[
0.2321,
0.119,
0.3909,
0.4418
],
[
0.4484,
0.1534,
0.506,
0.3307
]
],
"description": "Five pedestrians: two at far left, one center-left, prominent bag-carrying subject, and one crossing at center-right.",
"confidence": 0.91
},
"boxes_xyxy": [
[
36.99359893798828,
63.995399475097656,
64.00800323486328,
158.00399780273438
],
[
53.02080154418945,
54.999000549316406,
97.97760009765625,
153.9971923828125
],
[
106.99919891357422,
72.00900268554688,
135.9792022705078,
133.01820373535156
],
[
116.97840118408203,
44.981998443603516,
197.0135955810547,
167.00039672851562
],
[
225.9936065673828,
57.985198974609375,
255.0240020751953,
125.00460052490234
]
],
"sam_predicted_iou": [
0.84375,
0.9140625,
0.90625,
0.91015625,
0.8828125
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6493.png",
"routing_mask_path": "masks/IMG_6493_routing.png",
"raw_mask_fraction": 0.04955068447131939,
"routing_mask_fraction": 0.08179537246997565
}
transient_person · 2 semantic box(es) · raw 3.21% · route 4.77%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6494",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6494",
"boxes_norm_xyxy": [
[
0.1151,
0.2804,
0.2758,
0.6296
],
[
0.3611,
0.3254,
0.4067,
0.4841
]
],
"description": "Prominent pedestrian with hand bag plus one background pedestrian crossing behind tree.",
"confidence": 0.95
},
"boxes_xyxy": [
[
58.010398864746094,
105.99120330810547,
139.00320434570312,
237.98880004882812
],
[
181.99440002441406,
123.0011978149414,
204.976806640625,
182.98980712890625
]
],
"sam_predicted_iou": [
0.921875,
0.890625
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6494.png",
"routing_mask_path": "masks/IMG_6494_routing.png",
"raw_mask_fraction": 0.03208721760309062,
"routing_mask_fraction": 0.04769778281683044
}
transient_person · 6 semantic box(es) · raw 3.96% · route 6.84%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6495",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6495",
"boxes_norm_xyxy": [
[
0.0238,
0.4233,
0.0853,
0.6296
],
[
0.0575,
0.418,
0.1012,
0.619
],
[
0.1806,
0.418,
0.244,
0.6296
],
[
0.2401,
0.4074,
0.3373,
0.7354
],
[
0.3651,
0.4365,
0.4167,
0.6164
],
[
0.3948,
0.4259,
0.4444,
0.6085
]
],
"description": "Six pedestrians across the street area, including prominent subject with backpack/bag and two overlapping crossing pairs.",
"confidence": 0.88
},
"boxes_xyxy": [
[
11.995200157165527,
160.0074005126953,
42.9911994934082,
237.98880004882812
],
[
28.979999542236328,
158.00399780273438,
51.004798889160156,
233.98199462890625
],
[
91.02239990234375,
158.00399780273438,
122.97599792480469,
237.98880004882812
],
[
121.0103988647461,
153.9971923828125,
169.99920654296875,
277.981201171875
],
[
184.01040649414062,
164.9969940185547,
210.0167999267578,
232.99920654296875
],
[
198.9792022705078,
160.99020385742188,
223.97760009765625,
230.01300048828125
]
],
"sam_predicted_iou": [
0.87890625,
0.89453125,
0.84375,
0.90234375,
0.75,
0.82421875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6495.png",
"routing_mask_path": "masks/IMG_6495_routing.png",
"raw_mask_fraction": 0.039551314352901656,
"routing_mask_fraction": 0.06835789871504157
}
transient_person · 3 semantic box(es) · raw 2.90% · route 5.03%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6496",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6496",
"boxes_norm_xyxy": [
[
0.0,
0.5265,
0.0774,
0.7725
],
[
0.4107,
0.5503,
0.5317,
0.8492
],
[
0.5079,
0.5608,
0.5595,
0.709
]
],
"description": "Older pedestrian clipped at left, prominent pedestrian with backpack/bag, and one person immediately behind.",
"confidence": 0.92
},
"boxes_xyxy": [
[
0.0,
199.01699829101562,
39.00960159301758,
292.0050048828125
],
[
206.9927978515625,
208.01339721679688,
267.976806640625,
320.9975891113281
],
[
255.98159790039062,
211.98240661621094,
281.9880065917969,
268.00201416015625
]
],
"sam_predicted_iou": [
0.94140625,
0.890625,
0.84375
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6496.png",
"routing_mask_path": "masks/IMG_6496_routing.png",
"raw_mask_fraction": 0.029032291929117326,
"routing_mask_fraction": 0.05031704039640548
}
transient_person · 3 semantic box(es) · raw 1.74% · route 2.82%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6497",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6497",
"boxes_norm_xyxy": [
[
0.5774,
0.3069,
0.621,
0.4497
],
[
0.6111,
0.2989,
0.6627,
0.4471
],
[
0.6369,
0.2937,
0.748,
0.5397
]
],
"description": "Three overlapping pedestrians near center-right, including foreground subject and carried bag.",
"confidence": 0.91
},
"boxes_xyxy": [
[
291.0096130371094,
116.0082015991211,
312.9840087890625,
169.98660278320312
],
[
307.994384765625,
112.98419952392578,
334.00079345703125,
169.00379943847656
],
[
320.9975891113281,
111.01860046386719,
376.99200439453125,
204.00660705566406
]
],
"sam_predicted_iou": [
0.8828125,
0.87890625,
0.90625
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6497.png",
"routing_mask_path": "masks/IMG_6497_routing.png",
"raw_mask_fraction": 0.017421474762744603,
"routing_mask_fraction": 0.028192449819433946
}
transient_person · 2 semantic box(es) · raw 0.22% · route 0.75%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6498",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6498",
"boxes_norm_xyxy": [
[
0.5139,
0.4259,
0.5595,
0.5291
],
[
0.8234,
0.3862,
0.873,
0.5344
]
],
"description": "道路侧与右侧车辆旁各有一名虽小但边界可辨的行人。",
"confidence": 0.9
},
"boxes_xyxy": [
[
259.005615234375,
160.99020385742188,
281.9880065917969,
199.9998016357422
],
[
414.99359130859375,
145.9835968017578,
439.99200439453125,
202.00320434570312
]
],
"sam_predicted_iou": [
0.71875,
0.451171875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6498.png",
"routing_mask_path": "masks/IMG_6498_routing.png",
"raw_mask_fraction": 0.0021573444192491812,
"routing_mask_fraction": 0.00753233392122281
}
transient_person · 2 semantic box(es) · raw 0.68% · route 1.59%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6499",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6499",
"boxes_norm_xyxy": [
[
0.4246,
0.2328,
0.5079,
0.4101
],
[
0.8036,
0.1878,
0.8611,
0.381
]
],
"description": "喷泉后方及右侧车辆旁各有一名清晰可辨的行人。",
"confidence": 0.9
},
"boxes_xyxy": [
[
213.99839782714844,
87.99839782714844,
255.98159790039062,
155.01780700683594
],
[
405.014404296875,
70.9884033203125,
433.994384765625,
144.01800537109375
]
],
"sam_predicted_iou": [
0.82421875,
0.78125
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6499.png",
"routing_mask_path": "masks/IMG_6499_routing.png",
"raw_mask_fraction": 0.006760728982951205,
"routing_mask_fraction": 0.015941253044427648
}
no_prominent_transient · 0 semantic box(es) · raw 0.00% · route 0.00%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6500",
"cause": "no_prominent_transient",
"agent_record": null,
"boxes_xyxy": [],
"sam_predicted_iou": [],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6500.png",
"routing_mask_path": "masks/IMG_6500_routing.png",
"raw_mask_fraction": 0.0,
"routing_mask_fraction": 0.0
}
transient_person · 3 semantic box(es) · raw 2.93% · route 4.72%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6501",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6501",
"boxes_norm_xyxy": [
[
0.004,
0.4656,
0.1607,
0.836
],
[
0.4127,
0.4974,
0.4464,
0.5899
],
[
0.4365,
0.5053,
0.4821,
0.5952
]
],
"description": "Prominent pedestrian with bag at left and two cyclists in the background.",
"confidence": 0.89
},
"boxes_xyxy": [
[
2.0160000324249268,
175.99679565429688,
80.9927978515625,
316.00799560546875
],
[
208.00079345703125,
188.01719665527344,
224.985595703125,
222.98219299316406
],
[
219.99600219726562,
191.00340270996094,
242.9783935546875,
224.985595703125
]
],
"sam_predicted_iou": [
0.91796875,
0.75,
0.83203125
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6501.png",
"routing_mask_path": "masks/IMG_6501_routing.png",
"raw_mask_fraction": 0.029263248509280256,
"routing_mask_fraction": 0.04715713445872176
}
transient_person · 2 semantic box(es) · raw 2.43% · route 3.58%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6502",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6502",
"boxes_norm_xyxy": [
[
0.0794,
0.4656,
0.2302,
0.7698
],
[
0.6746,
0.5079,
0.7103,
0.5899
]
],
"description": "One pedestrian with bag at left and one background cyclist.",
"confidence": 0.94
},
"boxes_xyxy": [
[
40.017601013183594,
175.99679565429688,
116.02079772949219,
290.9844055175781
],
[
339.9984130859375,
191.9862060546875,
357.9912109375,
222.98219299316406
]
],
"sam_predicted_iou": [
0.90625,
0.875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6502.png",
"routing_mask_path": "masks/IMG_6502_routing.png",
"raw_mask_fraction": 0.02426618795666415,
"routing_mask_fraction": 0.035808767951625096
}
no_prominent_transient · 0 semantic box(es) · raw 0.00% · route 0.00%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6503",
"cause": "no_prominent_transient",
"agent_record": null,
"boxes_xyxy": [],
"sam_predicted_iou": [],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6503.png",
"routing_mask_path": "masks/IMG_6503_routing.png",
"raw_mask_fraction": 0.0,
"routing_mask_fraction": 0.0
}
transient_person · 1 semantic box(es) · raw 0.47% · route 0.88%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6504",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6504",
"boxes_norm_xyxy": [
[
0.7063,
0.0,
0.7817,
0.1429
]
],
"description": "Severely top-clipped pedestrian visible behind sculpture.",
"confidence": 0.86
},
"boxes_xyxy": [
[
355.9751892089844,
0.0,
393.976806640625,
54.01620101928711
]
],
"sam_predicted_iou": [
0.86328125
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6504.png",
"routing_mask_path": "masks/IMG_6504_routing.png",
"raw_mask_fraction": 0.004718862853783489,
"routing_mask_fraction": 0.008828840178046526
}
transient_person · 1 semantic box(es) · raw 0.42% · route 0.66%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6505",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6505",
"boxes_norm_xyxy": [
[
0.9544,
0.127,
1.0,
0.2619
]
],
"description": "Severely right-clipped pedestrian fragment with black bag.",
"confidence": 0.84
},
"boxes_xyxy": [
[
481.0176086425781,
48.00600051879883,
504.0,
98.99819946289062
]
],
"sam_predicted_iou": [
0.9453125
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6505.png",
"routing_mask_path": "masks/IMG_6505_routing.png",
"raw_mask_fraction": 0.0042412026539010664,
"routing_mask_fraction": 0.00655076845553036
}
transient_person · 1 semantic box(es) · raw 2.89% · route 3.92%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6506",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6506",
"boxes_norm_xyxy": [
[
0.881,
0.0,
1.0,
0.5608
]
],
"description": "Right-clipped pedestrian, including large black hand bag.",
"confidence": 0.96
},
"boxes_xyxy": [
[
444.02398681640625,
0.0,
504.0,
211.98240661621094
]
],
"sam_predicted_iou": [
0.91796875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6506.png",
"routing_mask_path": "masks/IMG_6506_routing.png",
"raw_mask_fraction": 0.028937809691777946,
"routing_mask_fraction": 0.03922587553539934
}
transient_person · 1 semantic box(es) · raw 2.29% · route 3.66%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6507",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6507",
"boxes_norm_xyxy": [
[
0.6091,
0.3995,
0.7361,
0.8333
]
],
"description": "One pedestrian beside the fountain, including backpack and carried black bag.",
"confidence": 0.97
},
"boxes_xyxy": [
[
306.98638916015625,
151.01100158691406,
370.994384765625,
314.9873962402344
]
],
"sam_predicted_iou": [
0.90234375
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6507.png",
"routing_mask_path": "masks/IMG_6507_routing.png",
"raw_mask_fraction": 0.022948685647098347,
"routing_mask_fraction": 0.036611866969009824
}
transient_person · 1 semantic box(es) · raw 2.02% · route 3.54%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6508",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6508",
"boxes_norm_xyxy": [
[
0.4167,
0.5952,
0.5794,
1.0
]
],
"description": "One pedestrian partially clipped at the bottom, including backpack and carried bag.",
"confidence": 0.96
},
"boxes_xyxy": [
[
210.0167999267578,
224.985595703125,
292.0176086425781,
378.0
]
],
"sam_predicted_iou": [
0.703125
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6508.png",
"routing_mask_path": "masks/IMG_6508_routing.png",
"raw_mask_fraction": 0.020229696816998405,
"routing_mask_fraction": 0.035441337028638616
}
transient_person · 1 semantic box(es) · raw 1.19% · route 1.67%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6509",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6509",
"boxes_norm_xyxy": [
[
0.5516,
0.0,
0.6964,
0.127
]
],
"description": "Visible upper fragment of the pedestrian at the top edge, including the black bag.",
"confidence": 0.91
},
"boxes_xyxy": [
[
278.00640869140625,
0.0,
350.985595703125,
48.00600051879883
]
],
"sam_predicted_iou": [
0.9296875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6509.png",
"routing_mask_path": "masks/IMG_6509_routing.png",
"raw_mask_fraction": 0.011910010917947425,
"routing_mask_fraction": 0.016718106995884774
}
transient_person · 1 semantic box(es) · raw 2.20% · route 3.21%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6510",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6510",
"boxes_norm_xyxy": [
[
0.5734,
0.0714,
0.7103,
0.3836
]
],
"description": "One pedestrian behind the fountain with a carried black bag and backpack.",
"confidence": 0.97
},
"boxes_xyxy": [
[
288.99359130859375,
26.989200592041016,
357.9912109375,
145.00079345703125
]
],
"sam_predicted_iou": [
0.9140625
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6510.png",
"routing_mask_path": "masks/IMG_6510_routing.png",
"raw_mask_fraction": 0.022003863273704544,
"routing_mask_fraction": 0.03210296464264718
}
transient_person · 1 semantic box(es) · raw 2.31% · route 3.28%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6511",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6511",
"boxes_norm_xyxy": [
[
0.623,
0.2698,
0.7738,
0.6058
]
],
"description": "One pedestrian with backpack and black hand-carried item.",
"confidence": 0.98
},
"boxes_xyxy": [
[
313.99200439453125,
101.9843978881836,
389.9952087402344,
228.99240112304688
]
],
"sam_predicted_iou": [
0.9375
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6511.png",
"routing_mask_path": "masks/IMG_6511_routing.png",
"raw_mask_fraction": 0.023100907029478458,
"routing_mask_fraction": 0.03283782648862014
}
transient_person · 1 semantic box(es) · raw 1.79% · route 2.63%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6512",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6512",
"boxes_norm_xyxy": [
[
0.5437,
0.4206,
0.6567,
0.7302
]
],
"description": "One pedestrian walking past the fountain, including backpack.",
"confidence": 0.98
},
"boxes_xyxy": [
[
274.0248107910156,
158.98680114746094,
330.976806640625,
276.0155944824219
]
],
"sam_predicted_iou": [
0.91796875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6512.png",
"routing_mask_path": "masks/IMG_6512_routing.png",
"raw_mask_fraction": 0.017899134962627027,
"routing_mask_fraction": 0.02634479717813051
}
transient_person · 1 semantic box(es) · raw 2.09% · route 3.22%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6513",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6513",
"boxes_norm_xyxy": [
[
0.373,
0.5344,
0.5099,
0.8651
]
],
"description": "One pedestrian with backpack and black carried bag.",
"confidence": 0.98
},
"boxes_xyxy": [
[
187.99200439453125,
202.00320434570312,
256.9895935058594,
327.0078125
]
],
"sam_predicted_iou": [
0.91015625
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6513.png",
"routing_mask_path": "masks/IMG_6513_routing.png",
"raw_mask_fraction": 0.020948811623414797,
"routing_mask_fraction": 0.03218694885361552
}
no_prominent_transient · 0 semantic box(es) · raw 0.00% · route 0.00%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6514",
"cause": "no_prominent_transient",
"agent_record": null,
"boxes_xyxy": [],
"sam_predicted_iou": [],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6514.png",
"routing_mask_path": "masks/IMG_6514_routing.png",
"raw_mask_fraction": 0.0,
"routing_mask_fraction": 0.0
}
no_prominent_transient · 0 semantic box(es) · raw 0.00% · route 0.00%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6515",
"cause": "no_prominent_transient",
"agent_record": null,
"boxes_xyxy": [],
"sam_predicted_iou": [],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6515.png",
"routing_mask_path": "masks/IMG_6515_routing.png",
"raw_mask_fraction": 0.0,
"routing_mask_fraction": 0.0
}
transient_person · 1 semantic box(es) · raw 1.27% · route 1.98%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6516",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6516",
"boxes_norm_xyxy": [
[
0.5734,
0.1746,
0.6548,
0.4312
]
],
"description": "One pedestrian partly occluded by the fountain structure, including backpack.",
"confidence": 0.96
},
"boxes_xyxy": [
[
288.99359130859375,
65.9988021850586,
330.0191955566406,
162.9936065673828
]
],
"sam_predicted_iou": [
0.91015625
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6516.png",
"routing_mask_path": "masks/IMG_6516_routing.png",
"raw_mask_fraction": 0.012655370790291425,
"routing_mask_fraction": 0.01979402872260015
}
transient_person · 1 semantic box(es) · raw 1.08% · route 1.87%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6517",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6517",
"boxes_norm_xyxy": [
[
0.3532,
0.3439,
0.4484,
0.5952
]
],
"description": "One pedestrian behind the fountain, including the black carried bag.",
"confidence": 0.96
},
"boxes_xyxy": [
[
178.01280212402344,
129.99420166015625,
225.9936065673828,
224.985595703125
]
],
"sam_predicted_iou": [
0.921875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6517.png",
"routing_mask_path": "masks/IMG_6517_routing.png",
"raw_mask_fraction": 0.010823465188544554,
"routing_mask_fraction": 0.018738977072310405
}
transient_person · 1 semantic box(es) · raw 1.25% · route 2.12%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6518",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6518",
"boxes_norm_xyxy": [
[
0.3294,
0.2513,
0.4345,
0.537
]
],
"description": "One pedestrian partly occluded by the arcing pipe, including bag and backpack.",
"confidence": 0.95
},
"boxes_xyxy": [
[
166.01759338378906,
94.99140167236328,
218.98800659179688,
202.98599243164062
]
],
"sam_predicted_iou": [
0.84375
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6518.png",
"routing_mask_path": "masks/IMG_6518_routing.png",
"raw_mask_fraction": 0.01248740236835475,
"routing_mask_fraction": 0.021164021164021163
}
transient_person · 1 semantic box(es) · raw 1.91% · route 3.38%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6519",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6519",
"boxes_norm_xyxy": [
[
0.4702,
0.2831,
0.6012,
0.6693
]
],
"description": "One pedestrian crossed by the fountain pipe, including black carried bag.",
"confidence": 0.97
},
"boxes_xyxy": [
[
236.98080444335938,
107.01180267333984,
303.0047912597656,
252.9954071044922
]
],
"sam_predicted_iou": [
0.8828125
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6519.png",
"routing_mask_path": "masks/IMG_6519_routing.png",
"raw_mask_fraction": 0.019069664902998235,
"routing_mask_fraction": 0.033787897875199466
}
transient_person · 1 semantic box(es) · raw 3.40% · route 5.16%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6520",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6520",
"boxes_norm_xyxy": [
[
0.7282,
0.0,
0.9306,
0.4841
]
],
"description": "One pedestrian clipped at the top and right-side area, including backpack and hand bag.",
"confidence": 0.96
},
"boxes_xyxy": [
[
367.0127868652344,
0.0,
469.02239990234375,
182.98980712890625
]
],
"sam_predicted_iou": [
0.88671875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6520.png",
"routing_mask_path": "masks/IMG_6520_routing.png",
"raw_mask_fraction": 0.0339716133366927,
"routing_mask_fraction": 0.05156105652137398
}
transient_person · 1 semantic box(es) · raw 0.30% · route 0.61%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6521",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6521",
"boxes_norm_xyxy": [
[
0.5575,
0,
0.6052,
0.127
]
],
"description": "上缘喷泉后方有清晰可辨的行人双腿。",
"confidence": 0.9
},
"boxes_xyxy": [
[
280.9800109863281,
0.0,
305.02081298828125,
48.00600051879883
]
],
"sam_predicted_iou": [
0.9140625
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6521.png",
"routing_mask_path": "masks/IMG_6521_routing.png",
"raw_mask_fraction": 0.0029814394893759974,
"routing_mask_fraction": 0.006130847400688671
}
transient_person · 1 semantic box(es) · raw 1.11% · route 1.79%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6522",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6522",
"boxes_norm_xyxy": [
[
0.3492,
0.2487,
0.4345,
0.4815
]
],
"description": "One pedestrian substantially occluded by the tree, including visible backpack.",
"confidence": 0.91
},
"boxes_xyxy": [
[
175.99679565429688,
94.00859832763672,
218.98800659179688,
182.0070037841797
]
],
"sam_predicted_iou": [
0.87890625
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6522.png",
"routing_mask_path": "masks/IMG_6522_routing.png",
"raw_mask_fraction": 0.011085915847820609,
"routing_mask_fraction": 0.017935878054925674
}
transient_person · 1 semantic box(es) · raw 1.36% · route 2.05%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6523",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6523",
"boxes_norm_xyxy": [
[
0.246,
0.4418,
0.3413,
0.7037
]
],
"description": "One pedestrian beside the tree with backpack.",
"confidence": 0.97
},
"boxes_xyxy": [
[
123.98400115966797,
167.00039672851562,
172.01519775390625,
265.99859619140625
]
],
"sam_predicted_iou": [
0.93359375
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6523.png",
"routing_mask_path": "masks/IMG_6523_routing.png",
"raw_mask_fraction": 0.013631687242798354,
"routing_mask_fraction": 0.0205026455026455
}
transient_person · 1 semantic box(es) · raw 1.15% · route 1.99%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6524",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6524",
"boxes_norm_xyxy": [
[
0.4504,
0.4392,
0.5516,
0.6905
]
],
"description": "One pedestrian beside the tree, including black bag and backpack.",
"confidence": 0.96
},
"boxes_xyxy": [
[
227.00160217285156,
166.01759338378906,
278.00640869140625,
261.0090026855469
]
],
"sam_predicted_iou": [
0.9140625
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6524.png",
"routing_mask_path": "masks/IMG_6524_routing.png",
"raw_mask_fraction": 0.01146909381036365,
"routing_mask_fraction": 0.019946250104980263
}
transient_person · 1 semantic box(es) · raw 2.47% · route 3.79%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6525",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6525",
"boxes_norm_xyxy": [
[
0.6468,
0.172,
0.7798,
0.5688
]
],
"description": "One pedestrian holding a black item in front, including backpack.",
"confidence": 0.98
},
"boxes_xyxy": [
[
325.9872131347656,
65.01599884033203,
393.0191955566406,
215.0063934326172
]
],
"sam_predicted_iou": [
0.921875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6525.png",
"routing_mask_path": "masks/IMG_6525_routing.png",
"raw_mask_fraction": 0.024712354077433444,
"routing_mask_fraction": 0.03794511631813219
}
transient_person · 1 semantic box(es) · raw 1.86% · route 2.89%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6526",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6526",
"boxes_norm_xyxy": [
[
0.504,
0.3598,
0.6409,
0.619
]
],
"description": "One pedestrian partly hidden by the tree and fountain, including carried item and backpack.",
"confidence": 0.94
},
"boxes_xyxy": [
[
254.01600646972656,
136.00439453125,
323.01361083984375,
233.98199462890625
]
],
"sam_predicted_iou": [
0.859375
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6526.png",
"routing_mask_path": "masks/IMG_6526_routing.png",
"raw_mask_fraction": 0.01861824976904342,
"routing_mask_fraction": 0.0289010665994793
}
transient_person · 1 semantic box(es) · raw 1.16% · route 2.25%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6527",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6527",
"boxes_norm_xyxy": [
[
0.5198,
0.1455,
0.6448,
0.4048
]
],
"description": "One pedestrian behind the tree-side fountain area, including backpack and black item.",
"confidence": 0.94
},
"boxes_xyxy": [
[
261.97918701171875,
54.999000549316406,
324.97918701171875,
153.014404296875
]
],
"sam_predicted_iou": [
0.87890625
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6527.png",
"routing_mask_path": "masks/IMG_6527_routing.png",
"raw_mask_fraction": 0.011579323087259594,
"routing_mask_fraction": 0.022528764592256657
}
no_prominent_transient · 0 semantic box(es) · raw 0.00% · route 0.00%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6528",
"cause": "no_prominent_transient",
"agent_record": null,
"boxes_xyxy": [],
"sam_predicted_iou": [],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6528.png",
"routing_mask_path": "masks/IMG_6528_routing.png",
"raw_mask_fraction": 0.0,
"routing_mask_fraction": 0.0
}
transient_person · 1 semantic box(es) · raw 0.76% · route 1.16%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6529",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6529",
"boxes_norm_xyxy": [
[
0.629,
0.0,
0.7063,
0.164
]
],
"description": "Top-edge fragment of the pedestrian visible behind the fountain.",
"confidence": 0.89
},
"boxes_xyxy": [
[
317.0159912109375,
0.0,
355.9751892089844,
61.992000579833984
]
],
"sam_predicted_iou": [
0.94140625
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6529.png",
"routing_mask_path": "masks/IMG_6529_routing.png",
"raw_mask_fraction": 0.007616318132191148,
"routing_mask_fraction": 0.011621315192743764
}
no_prominent_transient · 0 semantic box(es) · raw 0.00% · route 0.00%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6530",
"cause": "no_prominent_transient",
"agent_record": null,
"boxes_xyxy": [],
"sam_predicted_iou": [],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6530.png",
"routing_mask_path": "masks/IMG_6530_routing.png",
"raw_mask_fraction": 0.0,
"routing_mask_fraction": 0.0
}
transient_person · 1 semantic box(es) · raw 1.59% · route 2.35%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6531",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6531",
"boxes_norm_xyxy": [
[
0.5655,
0.0344,
0.6667,
0.2989
]
],
"description": "One pedestrian behind the fountain, including the raised black carried item.",
"confidence": 0.96
},
"boxes_xyxy": [
[
285.0119934082031,
13.003199577331543,
336.0168151855469,
112.98419952392578
]
],
"sam_predicted_iou": [
0.91796875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6531.png",
"routing_mask_path": "masks/IMG_6531_routing.png",
"raw_mask_fraction": 0.01586776685983035,
"routing_mask_fraction": 0.023452590912908373
}
transient_person · 1 semantic box(es) · raw 1.23% · route 1.98%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6532",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6532",
"boxes_norm_xyxy": [
[
0.5357,
0.3704,
0.6389,
0.6296
]
],
"description": "One pedestrian walking away, including backpack and raised black item.",
"confidence": 0.96
},
"boxes_xyxy": [
[
269.9927978515625,
140.01119995117188,
322.005615234375,
237.98880004882812
]
],
"sam_predicted_iou": [
0.9296875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6532.png",
"routing_mask_path": "masks/IMG_6532_routing.png",
"raw_mask_fraction": 0.01229843789367599,
"routing_mask_fraction": 0.019773032669858068
}
no_prominent_transient · 0 semantic box(es) · raw 0.00% · route 0.00%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6533",
"cause": "no_prominent_transient",
"agent_record": null,
"boxes_xyxy": [],
"sam_predicted_iou": [],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6533.png",
"routing_mask_path": "masks/IMG_6533_routing.png",
"raw_mask_fraction": 0.0,
"routing_mask_fraction": 0.0
}
transient_person · 1 semantic box(es) · raw 1.42% · route 1.95%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6534",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6534",
"boxes_norm_xyxy": [
[
0.2044,
0,
0.369,
0.1878
]
],
"description": "雕塑后方有上半身被画面裁切的近景行人及背包。",
"confidence": 0.9
},
"boxes_xyxy": [
[
103.0176010131836,
0.0,
185.9759979248047,
70.9884033203125
]
],
"sam_predicted_iou": [
0.9296875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6534.png",
"routing_mask_path": "masks/IMG_6534_routing.png",
"raw_mask_fraction": 0.014182833627278072,
"routing_mask_fraction": 0.019536827076509618
}
transient_person · 1 semantic box(es) · raw 2.30% · route 3.86%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6535",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6535",
"boxes_norm_xyxy": [
[
0.1032,
0.2275,
0.3075,
0.5661
]
],
"description": "One pedestrian left of the statue, including raised black item and extended arm.",
"confidence": 0.96
},
"boxes_xyxy": [
[
52.01279830932617,
85.99500274658203,
154.97999572753906,
213.9857940673828
]
],
"sam_predicted_iou": [
0.90625
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6535.png",
"routing_mask_path": "masks/IMG_6535_routing.png",
"raw_mask_fraction": 0.02302742084488116,
"routing_mask_fraction": 0.03862223901906441
}
transient_person · 1 semantic box(es) · raw 2.75% · route 4.09%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6536",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6536",
"boxes_norm_xyxy": [
[
0.121,
0.2116,
0.2579,
0.664
]
],
"description": "One pedestrian partly crossed by the pipe, including backpack and carried black item.",
"confidence": 0.97
},
"boxes_xyxy": [
[
60.98400115966797,
79.98480224609375,
129.98159790039062,
250.99200439453125
]
],
"sam_predicted_iou": [
0.921875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6536.png",
"routing_mask_path": "masks/IMG_6536_routing.png",
"raw_mask_fraction": 0.027531074158058284,
"routing_mask_fraction": 0.04093705383387923
}
transient_person · 1 semantic box(es) · raw 1.12% · route 1.50%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6537",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6537",
"boxes_norm_xyxy": [
[
0.252,
0,
0.373,
0.1534
]
],
"description": "雕塑后方有上缘裁切但清晰可辨的行人及背包。",
"confidence": 0.9
},
"boxes_xyxy": [
[
127.00800323486328,
0.0,
187.99200439453125,
57.985198974609375
]
],
"sam_predicted_iou": [
0.890625
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6537.png",
"routing_mask_path": "masks/IMG_6537_routing.png",
"raw_mask_fraction": 0.011217141177458638,
"routing_mask_fraction": 0.015043671789703535
}
transient_person · 1 semantic box(es) · raw 1.35% · route 2.25%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6538",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6538",
"boxes_norm_xyxy": [
[
0.2361,
0.2407,
0.3492,
0.5291
]
],
"description": "One pedestrian heavily occluded by the static statue, including raised black item.",
"confidence": 0.91
},
"boxes_xyxy": [
[
118.99440002441406,
90.9845962524414,
175.99679565429688,
199.9998016357422
]
],
"sam_predicted_iou": [
0.875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6538.png",
"routing_mask_path": "masks/IMG_6538_routing.png",
"raw_mask_fraction": 0.013489963886789283,
"routing_mask_fraction": 0.022492021499958006
}
transient_person · 1 semantic box(es) · raw 0.30% · route 0.61%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6539",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6539",
"boxes_norm_xyxy": [
[
0.1349,
0.2434,
0.1925,
0.3545
]
],
"description": "Small visible head-and-shoulder fragment of the pedestrian behind the statue.",
"confidence": 0.84
},
"boxes_xyxy": [
[
67.9896011352539,
92.00520324707031,
97.0199966430664,
134.00100708007812
]
],
"sam_predicted_iou": [
0.89453125
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6539.png",
"routing_mask_path": "masks/IMG_6539_routing.png",
"raw_mask_fraction": 0.0030234315948601664,
"routing_mask_fraction": 0.006136096413874192
}
transient_person · 1 semantic box(es) · raw 1.36% · route 2.19%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6540",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6540",
"boxes_norm_xyxy": [
[
0.0,
0.2222,
0.1032,
0.5053
]
],
"description": "One pedestrian clipped by the left image edge and partly hidden by the statue.",
"confidence": 0.92
},
"boxes_xyxy": [
[
0.0,
83.9916000366211,
52.01279830932617,
191.00340270996094
]
],
"sam_predicted_iou": [
0.8671875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6540.png",
"routing_mask_path": "masks/IMG_6540_routing.png",
"raw_mask_fraction": 0.013558201058201057,
"routing_mask_fraction": 0.021909381036365163
}
transient_person · 1 semantic box(es) · raw 1.32% · route 2.00%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6541",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6541",
"boxes_norm_xyxy": [
[
0.3433,
0.2619,
0.4563,
0.5291
]
],
"description": "One pedestrian beside the tree, including backpack and black carried item.",
"confidence": 0.96
},
"boxes_xyxy": [
[
173.023193359375,
98.99819946289062,
229.97520446777344,
199.9998016357422
]
],
"sam_predicted_iou": [
0.875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6541.png",
"routing_mask_path": "masks/IMG_6541_routing.png",
"raw_mask_fraction": 0.013169774082472495,
"routing_mask_fraction": 0.020035483329134122
}
transient_person · 1 semantic box(es) · raw 1.95% · route 3.31%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6542",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6542",
"boxes_norm_xyxy": [
[
0.0813,
0.1587,
0.2183,
0.4762
]
],
"description": "One pedestrian partly clipped at left, including backpack and bulky black carried item.",
"confidence": 0.96
},
"boxes_xyxy": [
[
40.97520065307617,
59.98860168457031,
110.02320098876953,
180.00360107421875
]
],
"sam_predicted_iou": [
0.90625
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6542.png",
"routing_mask_path": "masks/IMG_6542_routing.png",
"raw_mask_fraction": 0.019479087931468884,
"routing_mask_fraction": 0.033131771227009325
}
transient_person · 1 semantic box(es) · raw 2.02% · route 2.96%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6543",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6543",
"boxes_norm_xyxy": [
[
0.4187,
0.3228,
0.5536,
0.6481
]
],
"description": "One pedestrian beside the fountain, including backpack and black hand bag.",
"confidence": 0.98
},
"boxes_xyxy": [
[
211.02479553222656,
122.01840209960938,
279.014404296875,
244.98179626464844
]
],
"sam_predicted_iou": [
0.921875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6543.png",
"routing_mask_path": "masks/IMG_6543_routing.png",
"raw_mask_fraction": 0.020224447803812884,
"routing_mask_fraction": 0.02956244226085496
}
transient_person · 1 semantic box(es) · raw 3.70% · route 5.38%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6544",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6544",
"boxes_norm_xyxy": [
[
0.6012,
0.2487,
0.7937,
0.6746
]
],
"description": "One pedestrian crossed by the pipe, including backpack and large black hand bag.",
"confidence": 0.98
},
"boxes_xyxy": [
[
303.0047912597656,
94.00859832763672,
400.0248107910156,
254.99879455566406
]
],
"sam_predicted_iou": [
0.921875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6544.png",
"routing_mask_path": "masks/IMG_6544_routing.png",
"raw_mask_fraction": 0.03702653901066599,
"routing_mask_fraction": 0.053786638112034935
}
transient_person · 1 semantic box(es) · raw 1.16% · route 1.79%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6545",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6545",
"boxes_norm_xyxy": [
[
0.6071,
0.3942,
0.7123,
0.6111
]
],
"description": "One pedestrian behind the static statue and fountain, including carried bag.",
"confidence": 0.94
},
"boxes_xyxy": [
[
305.9783935546875,
149.00759887695312,
358.99920654296875,
230.9958038330078
]
],
"sam_predicted_iou": [
0.9140625
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6545.png",
"routing_mask_path": "masks/IMG_6545_routing.png",
"raw_mask_fraction": 0.01164756025867137,
"routing_mask_fraction": 0.017888636936255985
}
transient_person · 1 semantic box(es) · raw 0.89% · route 1.53%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6546",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6546",
"boxes_norm_xyxy": [
[
0.4921,
0.4101,
0.5873,
0.627
]
],
"description": "One pedestrian partly hidden behind the fountain, including backpack.",
"confidence": 0.94
},
"boxes_xyxy": [
[
248.01840209960938,
155.01780700683594,
295.99920654296875,
237.00599670410156
]
],
"sam_predicted_iou": [
0.90625
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6546.png",
"routing_mask_path": "masks/IMG_6546_routing.png",
"raw_mask_fraction": 0.008855085243974133,
"routing_mask_fraction": 0.015306122448979591
}
transient_person · 1 semantic box(es) · raw 1.06% · route 1.58%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6547",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6547",
"boxes_norm_xyxy": [
[
0.3155,
0.0,
0.4067,
0.164
]
],
"description": "Top-edge fragment of one pedestrian behind the fountain.",
"confidence": 0.89
},
"boxes_xyxy": [
[
159.01199340820312,
0.0,
204.976806640625,
61.992000579833984
]
],
"sam_predicted_iou": [
0.92578125
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6547.png",
"routing_mask_path": "masks/IMG_6547_routing.png",
"raw_mask_fraction": 0.010639749727051314,
"routing_mask_fraction": 0.015783782648862012
}
no_prominent_transient · 0 semantic box(es) · raw 0.00% · route 0.00%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6548",
"cause": "no_prominent_transient",
"agent_record": null,
"boxes_xyxy": [],
"sam_predicted_iou": [],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6548.png",
"routing_mask_path": "masks/IMG_6548_routing.png",
"raw_mask_fraction": 0.0,
"routing_mask_fraction": 0.0
}
transient_person · 2 semantic box(es) · raw 1.26% · route 2.28%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6549",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6549",
"boxes_norm_xyxy": [
[
0.1865,
0.1905,
0.2837,
0.4339
],
[
0.2698,
0.1958,
0.2996,
0.3016
]
],
"description": "Main pedestrian with backpack and black bag near the tree, plus one small background pedestrian confirmed transient against the render.",
"confidence": 0.88
},
"boxes_xyxy": [
[
93.99600219726562,
72.00900268554688,
142.98480224609375,
164.0142059326172
],
[
135.9792022705078,
74.01239776611328,
150.99839782714844,
114.00479888916016
]
],
"sam_predicted_iou": [
0.85546875,
0.87109375
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6549.png",
"routing_mask_path": "masks/IMG_6549_routing.png",
"raw_mask_fraction": 0.012592382632065172,
"routing_mask_fraction": 0.022833207357016883
}
transient_person · 4 semantic box(es) · raw 1.51% · route 2.77%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6550",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6550",
"boxes_norm_xyxy": [
[
0.2698,
0.545,
0.3651,
0.746
],
[
0.1448,
0.537,
0.1687,
0.6455
],
[
0.1726,
0.537,
0.2024,
0.6376
],
[
0.1964,
0.5317,
0.2262,
0.6376
]
],
"description": "Main pedestrian with backpack and bags, plus three distinct small background pedestrians removed in the clean render.",
"confidence": 0.87
},
"boxes_xyxy": [
[
135.9792022705078,
206.00999450683594,
184.01040649414062,
281.9880065917969
],
[
72.97920227050781,
202.98599243164062,
85.0248031616211,
243.99899291992188
],
[
86.99040222167969,
202.98599243164062,
102.00959777832031,
241.01280212402344
],
[
98.98560333251953,
200.98260498046875,
114.00479888916016,
241.01280212402344
]
],
"sam_predicted_iou": [
0.859375,
0.83203125,
0.90625,
0.90234375
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6550.png",
"routing_mask_path": "masks/IMG_6550_routing.png",
"raw_mask_fraction": 0.015080414882002183,
"routing_mask_fraction": 0.02769379356680944
}
transient_person · 1 semantic box(es) · raw 0.67% · route 1.14%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6551",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6551",
"boxes_norm_xyxy": [
[
0.4921,
0.3439,
0.5536,
0.5238
]
],
"description": "One pedestrian behind the fountain holding a black item.",
"confidence": 0.96
},
"boxes_xyxy": [
[
248.01840209960938,
129.99420166015625,
279.014404296875,
197.99639892578125
]
],
"sam_predicted_iou": [
0.921875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6551.png",
"routing_mask_path": "masks/IMG_6551_routing.png",
"raw_mask_fraction": 0.006729234903838079,
"routing_mask_fraction": 0.011369362559838751
}
transient_person · 1 semantic box(es) · raw 0.82% · route 1.39%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6552",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6552",
"boxes_norm_xyxy": [
[
0.369,
0.0053,
0.4583,
0.2037
]
],
"description": "喷泉后方有清晰行人,上半身可可靠识别。",
"confidence": 0.9
},
"boxes_xyxy": [
[
185.9759979248047,
2.0034000873565674,
230.9832000732422,
76.99859619140625
]
],
"sam_predicted_iou": [
0.89453125
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6552.png",
"routing_mask_path": "masks/IMG_6552_routing.png",
"raw_mask_fraction": 0.008214705635340555,
"routing_mask_fraction": 0.01389413790207441
}
transient_person · 1 semantic box(es) · raw 0.78% · route 1.31%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6553",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6553",
"boxes_norm_xyxy": [
[
0.4901,
0.2302,
0.5774,
0.3995
]
],
"description": "One pedestrian heavily occluded by the fountain, including black carried item.",
"confidence": 0.93
},
"boxes_xyxy": [
[
247.01040649414062,
87.0156021118164,
291.0096130371094,
151.01100158691406
]
],
"sam_predicted_iou": [
0.91796875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6553.png",
"routing_mask_path": "masks/IMG_6553_routing.png",
"raw_mask_fraction": 0.00781053162005543,
"routing_mask_fraction": 0.013122532963802806
}
no_prominent_transient · 0 semantic box(es) · raw 0.00% · route 0.00%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6554",
"cause": "no_prominent_transient",
"agent_record": null,
"boxes_xyxy": [],
"sam_predicted_iou": [],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6554.png",
"routing_mask_path": "masks/IMG_6554_routing.png",
"raw_mask_fraction": 0.0,
"routing_mask_fraction": 0.0
}
transient_person · 1 semantic box(es) · raw 0.76% · route 1.23%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6555",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6555",
"boxes_norm_xyxy": [
[
0.2242,
0.3651,
0.2956,
0.5317
]
],
"description": "One pedestrian mostly hidden behind the fountain, including black carried item.",
"confidence": 0.92
},
"boxes_xyxy": [
[
112.9968032836914,
138.00779724121094,
148.98240661621094,
200.98260498046875
]
],
"sam_predicted_iou": [
0.90625
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6555.png",
"routing_mask_path": "masks/IMG_6555_routing.png",
"raw_mask_fraction": 0.007569077013521458,
"routing_mask_fraction": 0.012287939867304946
}
transient_person · 1 semantic box(es) · raw 0.97% · route 1.59%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6556",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6556",
"boxes_norm_xyxy": [
[
0.3214,
0.5026,
0.4107,
0.6958
]
],
"description": "One pedestrian behind the fountain, including the raised black item.",
"confidence": 0.94
},
"boxes_xyxy": [
[
161.985595703125,
189.98280334472656,
206.9927978515625,
263.01239013671875
]
],
"sam_predicted_iou": [
0.90625
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6556.png",
"routing_mask_path": "masks/IMG_6556_routing.png",
"raw_mask_fraction": 0.009673931300915428,
"routing_mask_fraction": 0.015899260938943477
}
transient_person · 1 semantic box(es) · raw 0.78% · route 1.30%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6557",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6557",
"boxes_norm_xyxy": [
[
0.6091,
0.4206,
0.6885,
0.6138
]
],
"description": "One pedestrian partly hidden by the fountain and statue, including backpack.",
"confidence": 0.94
},
"boxes_xyxy": [
[
306.98638916015625,
158.98680114746094,
347.0039978027344,
232.0164031982422
]
],
"sam_predicted_iou": [
0.87109375
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6557.png",
"routing_mask_path": "masks/IMG_6557_routing.png",
"raw_mask_fraction": 0.007836776685983034,
"routing_mask_fraction": 0.012975560594608214
}
no_prominent_transient · 0 semantic box(es) · raw 0.00% · route 0.00%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6558",
"cause": "no_prominent_transient",
"agent_record": null,
"boxes_xyxy": [],
"sam_predicted_iou": [],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6558.png",
"routing_mask_path": "masks/IMG_6558_routing.png",
"raw_mask_fraction": 0.0,
"routing_mask_fraction": 0.0
}
transient_person · 1 semantic box(es) · raw 1.55% · route 2.57%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6559",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6559",
"boxes_norm_xyxy": [
[
0.2698,
0.3307,
0.377,
0.6481
]
],
"description": "One fully visible pedestrian with backpack and black carried item.",
"confidence": 0.98
},
"boxes_xyxy": [
[
135.9792022705078,
125.00460052490234,
190.00799560546875,
244.98179626464844
]
],
"sam_predicted_iou": [
0.94140625
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6559.png",
"routing_mask_path": "masks/IMG_6559_routing.png",
"raw_mask_fraction": 0.015468841857730746,
"routing_mask_fraction": 0.025662425464012765
}
no_prominent_transient · 0 semantic box(es) · raw 0.00% · route 0.00%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6560",
"cause": "no_prominent_transient",
"agent_record": null,
"boxes_xyxy": [],
"sam_predicted_iou": [],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6560.png",
"routing_mask_path": "masks/IMG_6560_routing.png",
"raw_mask_fraction": 0.0,
"routing_mask_fraction": 0.0
}
transient_person · 1 semantic box(es) · raw 24.69% · route 26.06%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6561",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6561",
"boxes_norm_xyxy": [
[
0.0,
0.0,
0.3929,
1.0
]
],
"description": "Large close pedestrian clipped by the left, top, and bottom image boundaries, including backpack strap and bulky hand-carried bag.",
"confidence": 0.98
},
"boxes_xyxy": [
[
0.0,
0.0,
198.0216064453125,
378.0
]
],
"sam_predicted_iou": [
0.98046875
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6561.png",
"routing_mask_path": "masks/IMG_6561_routing.png",
"raw_mask_fraction": 0.2469188292600991,
"routing_mask_fraction": 0.26057151255563954
}
transient_person · 1 semantic box(es) · raw 2.14% · route 2.93%
observed target
pose-nearest context
Raw 3DGS train render
Raw residual · auxiliary only
strong-agent semantic boxes
SAM semantic mask
+5 px initial routing mask
boundary candidate +5 px
boundary candidate +9 px
boundary candidate +13 px
boundary candidate +17 px
machine-readable record
{
"schema_version": "diag.agent_box_sam.v1",
"frame_id": "IMG_6569",
"cause": "transient_person",
"agent_record": {
"frame_id": "IMG_6569",
"boxes_norm_xyxy": [
[
0.25,
0.2143,
0.3631,
0.5026
]
],
"description": "One pedestrian behind the fountain, lower body occluded by the static basin.",
"confidence": 0.96
},
"boxes_xyxy": [
[
126.0,
81.00540161132812,
183.0023956298828,
189.98280334472656
]
],
"sam_predicted_iou": [
0.94140625
],
"sam_checkpoint": "/local/scratch-2/fy277/temp/diag3dgs/models/sam2.1/sam2.1_hiera_small.pt",
"sam_checkpoint_sha256": "6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38",
"base_dilation_px": 5,
"raw_mask_path": "masks/IMG_6569.png",
"routing_mask_path": "masks/IMG_6569_routing.png",
"raw_mask_fraction": 0.021368732678256487,
"routing_mask_fraction": 0.029341983707063073
}