About Me
I am a Ph.D. student at the State Key Lab of CAD & CG, Zhejiang University, supervised by Prof. Xiaowei Zhou, Sida Peng, and Hujun Bao. My research lies at the intersection of Computer Vision and Graphics, with a primary focus on generative human motion synthesis and physics-plausible behavior modeling.
Prior to ZJU, I earned my M.Sc. with Distinction in Computer Graphics from University College London (UCL) and a B.S. in Computer Science from Beihang University. Currently, I am dedicated to bridging the gap between raw human motion data and expressive, high-fidelity digital character animation.
Research Projects
Mocap-2-to-3
Zhumei Wang, Zechen Hu, , Huaijin Pi, Ziyong Feng, Liang Zhang, Mingtao Pei, Siyuan Huang
Multi-view lifting for monocular motion recovery with 2D pretraining. Novel approach for 3D motion capture data generation from sparse 2D inputs.
Motion-2-to-3
, Huaijin Pi, Zehong Shen, Qing Shuai, Zechen Hu, Zhumei Wang, Yajiao Dong, Ruizhen Hu, Taku Komura, Sida Peng, Xiaowei Zhou
Leveraging 2D motion data for 3D motion generation. Achieved SOTA results with 15% improvement in motion quality metrics.
User Motion Accentuation in Social Pointing Scenario
, Lisa Izzouzi, Anthony Steed
Real-time full-body motion generation from sparse tracking data. Achieved 92% user satisfaction in social VR scenarios.
Hand-by-Hand Mentor
, Jiahao Cui, Wanru Zhao, Shuai Li, Aimin Hao
AR-based piano training system with automatic gesture generation. Improved user accuracy by 85% in musical performance.
Technical Skills
Programming
- Proficient: Python, C++, LaTeX
- Experienced: C#, Java, MATLAB, JavaScript
Frameworks
- DL: PyTorch, TensorFlow
- CG: OpenGL, Unity3D, Blender
- Web: React, Node.js, Three.js
Research Areas
- 3D Motion Generation
- Computer Vision
- Augmented Reality
- Diffusion Models