GeezerVison is showing holmes969.github.io — Cheng Zhang
I am a Research Scientist at Meta Reality Labs, with broad research interests in inverse and differentiable rendering, 3D reconstruction with foundation models and agents, multimodal learning, and robot learning.
I received my Ph.D. in Computer Science from the University of California, Irvine in 2022, where I was advised by Prof. Shuang Zhao. My doctoral research focused on physics-based rendering and inverse rendering, particularly the recovery of geometry and material properties from physical measurements. To develop general and principled solutions to these inverse problems, I worked extensively on physics-based differentiable rendering. Prior to my Ph.D., I earned a B.E. in Electrical Engineering from Beijing University of Technology and an M.S. in Computer Science from Columbia University.
@article{li2026lsrm,title={LSRM: High-Fidelity Object-Centric Reconstruction via Scaled Context Windows},author={Li, Zhengqin and Zhang, Cheng and Engel, Jakob and Dong, Zhao},journal={arXiv preprint arXiv:2604.05182},year={2026},}
@inproceedings{li2026art,title={ART: Articulated Reconstruction Transformer},author={Li, Zizhang and Zhang, Cheng and Li, Zhengqin and Howard-Jenkins, Henry and Lv, Zhaoyang and Geng, Chen and Wu, Jiajun and Newcombe, Richard and Engel, Jakob and Dong, Zhao},booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},year={2026},}
@article{yan2025adaptive,title={Image-space Adaptive Sampling for Fast Inverse Rendering},author={Yan, Kai and Zhang, Cheng and Speierer, Sébastien and Cai, Guangyan and Zhu, Yufeng and Dong, Zhao and Zhao, Shuang},journal={ACM Transactions on Graphics},year={2025},note={SIGGRAPH 2025},}
Digital Twin Catalog: A Large-scale Photorealistic 3D Object Digital Twin Dataset
Zhao Dong, Ka Chen, Zhaoyang Lv, Hong-Xing Yu, Yunzhi Zhang, Cheng Zhang, Yufeng Zhu, Stephen Tian, Zhengqin Li, Geordie Moffatt, Sean Christofferson, James Fort, and 5 more authors
In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Hightlight Presentation, 2025
@inproceedings{dong2025digitaltwin,title={Digital Twin Catalog: A Large-scale Photorealistic 3D Object Digital Twin Dataset},author={Dong, Zhao and Chen, Ka and Lv, Zhaoyang and Yu, Hong-Xing and Zhang, Yunzhi and Zhang, Cheng and Zhu, Yufeng and Tian, Stephen and Li, Zhengqin and Moffatt, Geordie and Christofferson, Sean and Fort, James and Pan, Xiaqing and Yan, Mingfei and Wu, Jiajun and Ren, Carl Yuheng and Newcombe, Richard},booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, <span style="color: red;">Hightlight Presentation</span>},year={2025},}
@inproceedings{sun2023neuralpbir,title={Neural-PBIR Reconstruction of Shape, Material, and Illumination},author={Sun, Cheng and Cai, Guangyan and Li, Zhengqin and Yan, Kai and Zhang, Cheng and Marshall, Carl and Huang, Jia-Bin and Zhao, Shuang and Dong, Zhao},booktitle={International Conference on Computer Vision},year={2023},month=oct,}
@article{zhang2021antithetic,title={Antithetic Sampling for Monte Carlo Differentiable Rendering},author={Zhang, Cheng and Dong, Zhao and Doggett, Michael and Zhao, Shuang},journal={ACM Transactions on Graphics},volume={40},number={4},year={2021},month=aug,}
@article{zhang2021participatingmedia,title={Path-Space Differentiable Rendering of Participating Media},author={Zhang, Cheng and Yu, Zihan and Zhao, Shuang},journal={ACM Transactions on Graphics},volume={40},number={4},year={2021},month=aug,}
@article{zhang2020psdr,title={Path-Space Differentiable Rendering},author={Zhang, Cheng and Miller, Bailey and Yan, Kai and Gkioulekas, Ioannis and Zhao, Shuang},journal={ACM Transactions on Graphics},volume={39},number={4},year={2020},month=jul,}
@article{zhang2019radiative,title={A Differential Theory of Radiative Transfer},author={Zhang, Cheng and Wu, Lifan and Zheng, Changxi and Gkioulekas, Ioannis and Ramamoorthi, Ravi and Zhao, Shuang},journal={ACM Transactions on Graphics},volume={38},number={6},year={2019},}
Email is the best way to reach me.
You are visitor 01402503 — GeezerVison does not store the pages you look up. Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required.
