Computer Laboratory

Fangcheng Zhong


Research

With a broad interest in computer graphics and vision, machine learning and intelligence, and computational mathematics, my research spans the entire pipeline of extended reality (XR) --- from 3D scene acquisition, representation, and manipulation, to rendering and novel 3D displays. I am particularly interested in 1) hyper-realistic 3D imaging and rendering; 2) differentiable visual computing; 3) neural representations; 4) 3D generative AI; and 5) computational methods.

My PhD work was the first that established an end-to-end mixed reality system that successfully passed a visual Turing test, for which I was awarded the IEEE VGTC Virtual Reality Best Dissertation Honourable Mention.

About Me

I joined the Graphics & Interaction (Rainbow) Group at the University of Cambridge in 2018 as a Marie-Curie ITN Early Stage Researcher as part of the European ITN RealVision Project and completed a PhD in computer science advised by Prof. Rafał Mantiuk in 2021. My PhD was fully funded by the Marie Skłodowska-Curie Fellowship.

I am currently a senior researcher in the CORE Lab and an affiliated lecturer in the Department of Computer Science and Technology. I recently developed and led a new course on extended reality.

I keep my LinkedIn profile up to date with my full education/work experience.

Teaching

2022-23:

2023-24:

Supervision

2018-19:

2019-20:

2020-21:

2021-22:

2022-23:

2023-24:

Selected Publications


Hypernetworks for Generalizable BRDF Representation

Fazilet Gokbudak, Alejandro Sztrajman, Chenliang Zhou, Fangcheng Zhong, Rafal Mantiuk, Cengiz Oztireli

arXiv, 2023

[Page][Paper]


Differentiable Visual Computing for Inverse Problems and Machine Learning

Andrew Spielberg, Fangcheng Zhong, Konstantinos Rematas, Krishna Murthy Jatavallabhula, Cengiz Oztireli, Tzu-Mao Li, Derek Nowrouzezahrai

Nature Machine Intelligence, 2023

[Paper]


Neural Fields with Hard Constraints of Arbitrary Differential Order

Fangcheng Zhong, Kyle Fogarty, Param Hanji, Tianhao Wu, Alejandro Sztrajman, Andrew Spielberg, Andrea Tagliasacchi, Petra Bosilj, Cengiz Oztireli

Proceedings of the Conference on Neural Information Processing Systems (NeurIPS), 2023

[Page][Paper]




ARF-Plus: Controlling Perceptual Factors in Artistic Radiance Fields for 3D Scene Stylization

Wenzhao Li, Tianhao Wu, Fangcheng Zhong, Cengiz Oztireli

arXiv, 2023

[Paper]





αSurf: Implicit Surface Reconstruction for Semi-Transparent and Thin Objects with Decoupled Geometry and Opacity

Tianhao Wu, Hanxue Liang, Fangcheng Zhong, Gernot Riegler, Shimon Vainer, Cengiz Oztireli

arXiv, 2023

[Page][Paper]





CLIP-PAE: Projection-Augmentation Embedding to Extract Relevant Features for a Disentangled, Interpretable, and Controllable Text-Guided Face Manipulation

Chenliang Zhou, Fangcheng Zhong, Cengiz Oztireli

Proceedings of ACM SIGGRAPH, 2023

[Page][Paper]





D2NeRF: Self-Supervised Decoupling of Dynamic and Static Objects from a Monocular Video

Tianhao Wu, Fangcheng Zhong, Andrea Tagliasacchi, Forrester Cole, Cengiz Oztireli

Proceedings of the Conference on Neural Information Processing Systems (NeurIPS), 2022

[Page][Paper]


Dark Stereo: Improving Depth Perception under Low Luminance

Krzysztof Wolski, Fangcheng Zhong, Karol Myszkowski, Rafał K. Mantiuk

ACM Transactions on Graphics (Proceedings of ACM SIGGRAPH), 2022

[Page][Paper]



Kubric: a Scalable Dataset Generator

Klaus Greff, Francois Belletti, Lucas Beyer, Carl Doersch, Yilun Du, Daniel Duckworth, David J. Fleet, Dan Gnanapragasam, Florian Golemo, Charles Herrmann, Thomas Kipf, Abhijit Kundu, Dmitry Lagun, Issam Laradji, Hsueh-Ti (Derek) Liu, Henning Meyer, Yishu Miao, Derek Nowrouzezahrai, Cengiz Oztireli, Etienne Pot, Noha Radwan, Daniel Rebain, Sara Sabour, Mehdi S. M. Sajjadi, Matan Sela, Vincent Sitzmann, Austin Stone, Deqing Sun, Suhani Vora, Ziyu Wang, Tianhao Wu, Kwang Moo Yi, Fangcheng Zhong, Andrea Tagliasacchi

Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), 2022

[Page][Paper]





Reproducing Reality with a High-Dynamic-Range Multi-Focal Stereo Display

Fangcheng Zhong, Akshay Jindal, Özgür Yöntem, Param Hanji, Simon Watt, Rafał K. Mantiuk

ACM Transactions on Graphics (Proceedings of ACM SIGGRAPH Asia), 2021

[Page][Paper]



Noise-Aware Merging of High Dynamic Range Image Stacks without Camera Calibration

Param Hanji, Fangcheng Zhong, Rafał K. Mantiuk

Proceedings of the European Conference on Computer Vision (ECCV) Workshops, 2020

[Page][Paper]


DiCE: Dichoptic Contrast Enhancement for VR and Stereo Displays

Fangcheng Zhong, George Alex Koulieris, George Drettakis, Martin S. Banks, Fredo Durand, Rafał K. Mantiuk

ACM Transactions on Graphics (Proceedings of ACM SIGGRAPH Asia), 2019

[Page][Paper]


Dissertation

Path from Photorealism to Perceptual Realism

Fangcheng Zhong

IEEE VGTC Virtual Reality Best Dissertation Honourable Mention

[Apollo][Full Text][Full Text (compressed)]


Contact

Email: fangcheng [dot] zhong [at] cst [dot] cam [dot] ac [dot] uk
Phone: +44 (0)1223 763659
Office: SS13, Computer Laboratory
Address: Computer Laboratory, William Gates Building, 15 JJ Thomson Ave, Cambridge CB3 0FD

  • © 2018 Computer Laboratory, University of Cambridge