👨‍🎓 About me

I received my M.S. degree in Electronic Information (Artificial Intelligence) from Tsinghua University in 2026, under the guidance of Prof. Haoqian Wang. I got B.Eng. degree in Robot Engineering at South China University of Technology .

Currently I work at XPeng GWM team.

My research interests lie in world models, video generation, and 3D vision.


đź’» Experience

  • 2024.08 ~ 2025.03, I was a research intern at the IDEA, advised by Yu Li and Yunfei Liu.
  • 2025.07 ~ 2026.03, I was a research intern at the WeChat Vision, Tencent Inc.


📝 Publications

ECCV 2026
sym

EMOSH: Expressive Motion and Shape Disentanglement for Human Animation
Dongbin Zhang, Hao Liu, Binquan Dai, Kangjie Chen, Chuming Wang, Chen Li†, Jing LYU, Haoqian Wang†
Page Paper

- EMOSH achieves high-fidelity, mesh-guided expressive human animation with explicit motion-shape disentanglement, preventing body shape leakage from the driving subject.

ICCV 2025
sym

GUAVA: Generalizable Upper Body 3D Gaussian Avatar
Dongbin Zhang, Yunfei Liu†, Lijian Lin, Ye Zhu, Yang Li, Minghan Qin, Yu Li‡, Haoqian Wang†
Page Paper

- We propose GUAVA, the first framework for fast animatable upper-body 3D Gaussian avatar reconstruction from a single image.

CVPR 2025
sym

HRAvatar: High-Quality and Relightable Gaussian Head Avatar
Dongbin Zhang, Yunfei Liu, Lijian Lin, Ye Zhu, Kangjie Chen, Minghan Qin, Yu Li†, Haoqian Wang†
Page Paper Code

- With monocular video input, HRAvatar reconstructs a high-quality, animatable 3D head avatar that enables realistic relighting effects and simple material editing.

ECCV 2024
sym

Gaussian in the Wild: 3D Gaussian Splatting for Unconstrained Image Collections
Dongbin Zhang* , Chuming Wang*, Weitao Wang, Peihao Li, Minghan Qin, Haoqian Wang†
Page Paper Code

- GS-W utilizes 3D Gaussian Splatting with introduced separated intrinsic and dynamic appearance to reconstruct scenes from uncontrolled images, achieving high-quality results.

🏆 Honors and Awards