Projects
ColorVideoVDP-ML: Visual Difference Predictor with a neural regressor for image and video quality prediction
Dounia Hammou(1), Fei Yin(1), and Rafał K. Mantiuk(1).
(1)University of Cambridge
Presented at the 2025 IEEE International Conference on Multimedia and Expo Workshops (ICMEW) [Second place in ICME Generalizable HDR & SDR Video Quality Measurement Grand Challenge]
Abstract
ColorVideoVDP-ML is a full-reference image and video quality metric, which combines a visual difference predictor with a machine learning regressor. It employs ColorVideoVDP as an encoder of visual information and visible differences, and a neural architecture as a regressor of the final quality scores. It benefits from low-level vision models of contrast sensitivity and masking, found in ColorVideoVDP, as well as its ability to handle both SDR and HDR content, and to adapt to arbitrary viewing conditions, display resolution, and size. Two neural regressors, one based on MLPs and one on Transformers, are trained on multiple video and image quality datasets, all scaled in the Just-Objectionable-Difference (JOD) units. The regressors let us account for higher-level factors influencing perceived image quality, such as saliency or texture differences, and provide a way to fine-tune and specialize the metric in handling a specific type of distortions.
ICMEW 2025 Presentation
Materials
- Paper:
ColorVideoVDP-ML: Visual Difference Predictor with a neural regressor for image and video quality prediction.
Dounia Hammou, Fei Yin, Rafał K. Mantiuk.
In 2025 IEEE International Conference on Multimedia and Expo Workshops (ICMEW), pp. 1-6
[DOI] [paper PDF] - Code [Github]
Related projects
- ColorVideoVDP - A visual difference predictor for image, video and display distortions
- FovVideoVDP - Foveated Video Visual Difference Predictor
- DPVM - Deep Photometric Visual Metric
- HDR-VDP - A Visual Difference Predictor for High Dynamic Range Images
- castleCSF - A Contrast Sensitivity Function of Color, Area, Spatio-Temporal frequency, Luminance and Eccentricity - models contrast sensitivity in ColorVideoVDP