Digital human · Generative AI
I received my Ph.D. in Computer Science and Technology from Zhejiang University in 2026, advised by Prof. Xiaogang Jin. I received my B.S. from Chu Kochen College, Zhejiang University, in 2021.
In 2025, I interned at Codec Avatars Lab, Meta, working with Junxuan Li. From 2024 to 2025, I was an academic guest at ETH Zürich’s Computer Vision and Learning Group, working with Prof. Siyu Tang.
I’m always happy to explore potential research collaborations—let’s get in touch.
Outside research, I enjoy painting.
My doctoral research has focused on the generation and editing of high-quality, realistic digital humans, spanning 2D portraits, static and dynamic digital humans, and large-scale multi-modal model training.
I am now expanding this line of research toward broader questions in generative modeling, world models, and emerging directions in AI.
Research Scientist Intern · with Junxuan Li
Academic Guest · with Prof. Siyu Tang
Ph.D., Computer Science & Technology
State Key Lab of CAD&CG
B.S., Computer Science & Technology
Chu Kochen College
European Conference on Computer Vision (ECCV) 2026
A diffusion-based generative model for generating and editing photorealistic full-body avatars from text and image inputs.
ACM SIGGRAPH (Conference Track) 2025
A novel framework, AnimPortrait3D, for text-based realistic animatable 3DGS avatar generation with morphable model alignment.
IEEE Transactions on Circuits and Systems for Video Technology 2025
The first 3D-aware one-quarter headshot portrait generator that learns a canonical 3D avatar distribution from the 360°PHQ dataset with body pose self-learning.
ACM Transactions on Graphics (Proceedings of SIGGRAPH) 2024
A novel neural rendering-based framework with a novel joint geometry-appearance prior to achieve text-to-3D-portrait generation.
IEEE/CVF International Conference on Computer Vision (ICCV) 2023
A large-pose Flickr face dataset comprised of 19,590 high-quality real large-pose portrait images.
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022
A dataset and a baseline method for removing hair from portrait images using generative adversarial networks (GANs).
ACM Transactions on Graphics (Proceedings of SIGGRAPH) 2021
A novel method that can automatically remove the double chin effect in portrait images.