Selected Publications
*Equal contribution †Corresponding author
|
PanoLAM: Large Avatar Model for Gaussian Full-Head Synthesis from One-shot Unposed Image
To be released
|
|
SyncHuman: Synchronizing 2D and 3D Diffusion Models for Single-view Human Reconstruction
Arxiv 2025
|
|
CMD: Controllable Multiview Diffusion for 3D Editing and Progressive Generation
ACM SIGGRAPH, 2025
|
|
Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control
ACM SIGGRAPH, 2025
|
|
Align3R: Aligned Monocular Depth Estimation for Dynamic Videos
IEEE CVPR 2025, Highlight
|
|
PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion
IEEE CVPR 2025
|
|
Era3D: High-Resolution Multiview Diffusion using Efficient Row-wise Attention
NeurIPS 2024
|
![]() |
Weakly-Supervised Emotion Transition Learning for Diverse 3D Co-speech Gesture Generation
IEEE CVPR 2024
|
![]() |
OPAL: Occlusion Pattern Aware Loss for Unsupervised Light Field Disparity Estimation
IEEE-TPAMI 2023
|
![]() |
Learning Visibility Field for Detailed 3D Human Reconstruction and Relighting
IEEE CVPR 2023
|
Experiences
![]() |
Research Intern, VAST AI
Beijing, China
Aug. 2023 - May. 2024
Host by Dr. Yangguang Li and Dr. Yanpei Cao
|
![]() |
Research Intern, Alibaba Tongyi lab
Hangzhou, China
Feb. 2025 - Present
Host by Dr. Zilong Dong and Dr. Yisheng He
|
![]() |
Incoming Research Scientist Intern, Meta Reality Lab
Pittsburgh, US
Host by Dr. Shunsuke Saito
|