About Me
I am a third-year Ph.D. student in the Department of Computer Science and Technology at Tsinghua University, working in the CSCG Group under the supervision of Prof. Shi-Min Hu.
My research lies at the intersection of computer graphics and generative AI, with a focus on 3D characters: generating them, rigging them, and bringing them to life with animation. I am especially interested in technologies for games and virtual characters, like VTubers, aiming to bring people a better digital entertainment experience.
If you are interested in 3D characters, rigging, animation, or VTuber research, feel free to contact me!
News
- Our paper on transferring the intelligence of VLMs to robotic control is released on arXiv. Check the project page.
- TopoCap is accepted to SIGGRAPH 2026: motion capture from monocular video onto characters with arbitrary skeletal topologies.
- CharacterGen is accepted to SIGGRAPH 2024 (ACM TOG).
Publications
Full list on Google Scholar.
Transferring the Intelligence of VLMs to Robotic Control
Studies whether the intelligence of vision-language models can carry over from the digital world to physical robotic control.
TopoCap: Learning Topology-Agnostic Motion Priors for Monocular Video-to-Animation
Captures motion from monocular video and retargets it onto characters with arbitrary, unseen skeletal topologies, from bipeds to hexapods, without test-time optimization.
SkinTokens: A Learned Compact Representation for Unified Autoregressive Rigging
A discrete, compact representation of skinning weights that turns rigging into token prediction, unifying skeleton and skinning generation in one autoregressive model.
One Model to Rig Them All: Diverse Skeleton Rigging with UniRig
A single model that automatically rigs diverse 3D assets, from humans and animals to inanimate objects, with skeletons and skinning weights.
CharacterGen: Efficient 3D Character Generation from Single Images with Multi-View Pose Canonicalization
Generates a pose-canonicalized 3D character mesh from a single image, ready for downstream rigging and animation.
Beyond Research
Research taste
AIGC work with direct visual impact: things you can see, play with, and animate.
Sports
Badminton, skating, and swimming.
Entertainment
Games, VR/AR, and virtual livestreaming.