- DyCrowd: A framework for spatio-temporally consistent 3D reconstruction of hundreds of individuals' poses, positions, and shapes from a large-scene video
- RESCUE: A real-time 3D crowd evacuation simulation framework that integrates a 3D-adaptive SFM Decision Mechanism and a Personalized Gait Control Motor
- LoGAvatar: A novel framework designed to enhance both geometry and texture modeling and editing of human avatars
- FOF-X: A new reconstruction framework that mitigates performance degradation caused by texture and lighting effects
- EMP3D: A new dataset capturing the intricate movements of rescuers during emergency procedures with 3D poses and shapes
- VIPTour: An AI-driven system facilitating people with blindness and low vision in interpreting and experiencing unfamiliar environments
Research Experience
Extensive research experience in the field of digital humans, having participated in multiple significant research projects.
Background
Professor at the College of Intelligence and Computing, Tianjin University (Peiyang University), with research interests in digital humans, 3D reconstruction, etc.