Peng Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Peng Li has a total of 42 co-authors. Here are the top co-authors by number of shared publications:
- Yuan Liu
Hong Kong University of Science and Technology, Hong Kong, Hong Kong
4 shared publications - Zekai Gu
Hong Kong University of Science and Technology, Hong Kong, Hong Kong
3 shared publications - Cheng Lin
Macau University of Science and Technology, Macau, Macao
2 shared publications - Jiahao Lu
The Hong Kong University of Science and Technology
2 shared publications - Wenping Wang
Texas A&M University, College Station, USA
2 shared publications - Alla Sheffer
University of British Columbia, Vancouver, Canada
1 shared publication
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 16334-16343
PURE: Refining Feed-forward 3D Reconstruction with Unlabeled Post-training
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 16334-16343
Open AccessPURE: Refining Feed-forward 3D Reconstruction with Unlabeled Post-training
- 1 October 2026
- Published by Springer Nature
- p. 360-380
LUNA: Learning Universal 3D Human Animation Beyond Skinning
- 1 October 2026
- Published by Springer Nature
- p. 360-380
LUNA: Learning Universal 3D Human Animation Beyond Skinning
- 10 September 2026
- Published by Springer Nature
- p. 661-677
FlexAM: Flexible Appearance-Motion Decomposition for Versatile Video Generation Control
- 10 September 2026
- Published by Springer Nature
- p. 661-677
FlexAM: Flexible Appearance-Motion Decomposition for Versatile Video Generation Control
- Top Cited PapersOpen Access
- 27 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control
- 27 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Top Cited PapersOpen AccessDiffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control
- Open Access
- 27 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-10
CMD: Controllable Multiview Diffusion for 3D Editing and Progressive Generation
- 27 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Open AccessCMD: Controllable Multiview Diffusion for 3D Editing and Progressive Generation
- 18 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 46 (2) , 681-694
OPAL: Occlusion Pattern Aware Loss for Unsupervised Light Field Disparity Estimation
Light field disparity estimation is an essential task in computer vision. Currently, supervised learning-based methods have achieved better performance than both unsupervised and optimization-based methods. However, the generalization capacity of supervised methods on real-world data, where no ground truth is available for training, remains limited. In this paper, we argue that unsupervised methods can achieve not only much stronger generalization capacity on real-world data but also more accurate disparity estimation results on synthetic datasets. To fulfill this goal, we present the O cclusion P attern A ware L oss, named OPAL, which successfully extracts and encodes general occlusion patterns inherent in the light field for calculating the disparity loss. OPAL enables: i) accurate and robust disparity estimation by teaching the network how to handle occlusions effectively and ii) significantly reduced network parameters required for accurate and efficient estimation. We further propose an EPI transformer and a gradient-based refinement module for achieving more accurate and pixel-aligned disparity estimation results. Extensive experiments demonstrate our method not only significantly improves the accuracy compared with SOTA unsupervised methods, but also possesses stronger generalization capacity on real-world data compared with SOTA supervised methods. Last but not least, the network training and inference efficiency are much higher than existing learning-based methods. Our code will be made publicly available.
- 18 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 46 (2) , 681-694
OPAL: Occlusion Pattern Aware Loss for Unsupervised Light Field Disparity Estimation
Light field disparity estimation is an essential task in computer vision. Currently, supervised learning-based methods have achieved better performance than both unsupervised and optimization-based methods. However, the generalization capacity of supervised methods on real-world data, where no ground truth is available for training, remains limited. In this paper, we argue that unsupervised methods can achieve not only much stronger generalization capacity on real-world data but also more accurate disparity estimation results on synthetic datasets. To fulfill this goal, we present the O cclusion P attern A ware L oss, named OPAL, which successfully extracts and encodes general occlusion patterns inherent in the light field for calculating the disparity loss. OPAL enables: i) accurate and robust disparity estimation by teaching the network how to handle occlusions effectively and ii) significantly reduced network parameters required for accurate and efficient estimation. We further propose an EPI transformer and a gradient-based refinement module for achieving more accurate and pixel-aligned disparity estimation results. Extensive experiments demonstrate our method not only significantly improves the accuracy compared with SOTA unsupervised methods, but also possesses stronger generalization capacity on real-world data compared with SOTA supervised methods. Last but not least, the network training and inference efficiency are much higher than existing learning-based methods. Our code will be made publicly available.