Yiqun Zhao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yiqun Zhao has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Binbin Huang
University of Hong Kong, Hong Kong SAR, China
2 shared publications - Shenghua Gao
The University of Hong Kong
2 shared publications - Yihao Zhi
The Chinese University of Hong Kong
2 shared publications - Chen Zhao
Department of Computer Vision Technology (VIS), Baidu Inc., Beijing, China
1 shared publication - Chenming Wu
Baidu, Beijing, China
1 shared publication Jingdong Wang
Department of Computer Vision Technology (VIS), Baidu Inc., Beijing, China
1 shared publication
Latest Publications
- 14 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (12) , 11502-11518
Surfel-Based Gaussian Inverse Rendering for Fast and Relightable Dynamic Human Reconstruction From Monocular Videos
Efficient and accurate reconstruction of a relightable, dynamic clothed human avatar from a monocular video is crucial for the entertainment industry. This article presents SGIA (Surfel-based Gaussian Inverse Avatar), which introduces efficient training and rendering for relightable dynamic human reconstruction. SGIA advances previous Gaussian Avatar methods by comprehensively modeling Physically-Based Rendering (PBR) properties for clothed human avatars, allowing for the manipulation of avatars into novel poses under diverse lighting conditions. Specifically, our approach integrates pre-integration and image-based lighting for fast light calculations that surpass the performance of existing implicit-based techniques. To address challenges related to material lighting disentanglement and accurate geometry reconstruction, we propose an innovative occlusion approximation strategy and a progressive training approach. Extensive experiments demonstrate that SGIA not only achieves highly accurate physical properties but also significantly enhances the realistic relighting of dynamic human avatars, providing a substantial speed advantage.
- 14 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (12) , 11502-11518
Surfel-Based Gaussian Inverse Rendering for Fast and Relightable Dynamic Human Reconstruction From Monocular Videos
Efficient and accurate reconstruction of a relightable, dynamic clothed human avatar from a monocular video is crucial for the entertainment industry. This article presents SGIA (Surfel-based Gaussian Inverse Avatar), which introduces efficient training and rendering for relightable dynamic human reconstruction. SGIA advances previous Gaussian Avatar methods by comprehensively modeling Physically-Based Rendering (PBR) properties for clothed human avatars, allowing for the manipulation of avatars into novel poses under diverse lighting conditions. Specifically, our approach integrates pre-integration and image-based lighting for fast light calculations that surpass the performance of existing implicit-based techniques. To address challenges related to material lighting disentanglement and accurate geometry reconstruction, we propose an innovative occlusion approximation strategy and a progressive training approach. Extensive experiments demonstrate that SGIA not only achieves highly accurate physical properties but also significantly enhances the realistic relighting of dynamic human avatars, providing a substantial speed advantage.
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 3761-3770
HeroMaker: Human-centric Video Editing with Motion Priors
Video generation and editing, particularly human-centric video editing, has seen a surge of interest in its potential to create immersive and dynamic content. A fundamental challenge is ensuring temporal coherence and visual harmony across frames, especially in handling large-scale human motion and maintaining consistency over long sequences. The previous methods, such as zero-shot text-to-video methods with diffusion model, struggle with flickering and length limitations. In contrast, methods employing Video-2D representations grapple with accurately capturing complex structural relationships in large-scale human motion. Simultaneously, some patterns on the human body appear intermittently throughout the video, posing a knotty problem in identifying visual correspondence. To address the above problems, we present HeroMaker. This human-centric video editing framework manipulates the person's appearance within the input video and achieves consistent results across frames. Specifically, we propose to learn the motion priors, which represent the correspondences between dual canonical fields and each video frame, by leveraging the body mesh-based human motion warping and neural deformation-based margin refinement in the video reconstruction framework to ensure the semantic correctness of canonical fields. HeroMaker performs human-centric video editing by manipulating the dual canonical fields and combining them with motion priors to synthesize temporally coherent and visually plausible results. Comprehensive experiments demonstrate that our approach surpasses existing methods regarding temporal consistency, visual quality, and semantic coherence.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 3761-3770
Open AccessHeroMaker: Human-centric Video Editing with Motion Priors
Video generation and editing, particularly human-centric video editing, has seen a surge of interest in its potential to create immersive and dynamic content. A fundamental challenge is ensuring temporal coherence and visual harmony across frames, especially in handling large-scale human motion and maintaining consistency over long sequences. The previous methods, such as zero-shot text-to-video methods with diffusion model, struggle with flickering and length limitations. In contrast, methods employing Video-2D representations grapple with accurately capturing complex structural relationships in large-scale human motion. Simultaneously, some patterns on the human body appear intermittently throughout the video, posing a knotty problem in identifying visual correspondence. To address the above problems, we present HeroMaker. This human-centric video editing framework manipulates the person's appearance within the input video and achieves consistent results across frames. Specifically, we propose to learn the motion priors, which represent the correspondences between dual canonical fields and each video frame, by leveraging the body mesh-based human motion warping and neural deformation-based margin refinement in the video reconstruction framework to ensure the semantic correctness of canonical fields. HeroMaker performs human-centric video editing by manipulating the dual canonical fields and combining them with motion priors to synthesize temporally coherent and visually plausible results. Comprehensive experiments demonstrate that our approach surpasses existing methods regarding temporal consistency, visual quality, and semantic coherence.