Yilin Wang
PhD Candidate, 3D Generative AI · University of Alberta (Vision and Learning Lab) · yilin32@ualberta.ca · Google Scholar · GitHub · LinkedIn
I am a PhD candidate from the Vision and Learning Lab at the University of Alberta, supervised by Prof. Li Cheng. My research interests lie in Generative AI for 3D computer vision and animation, especially 3D human motion generation, human–object interaction, and character animation.
News
- 2025‑01 — Our paper MotionDreamer is accepted to ICLR 2025.
- 2024‑08 — Our paper RegionGrasp is accepted to ECCV 2024 Workshop.
- 2024‑07 — Our paper GSD is accepted to ECCV 2024.
Publications
MotionDreamer: One-to-Many Motion Synthesis with Localized Generative Masked Transformer
Yilin Wang, Chuan Guo, Yuxuan Mu, Muhammad Gohar Javed, Xinxin Zuo, Juwei Lu, Hai Jiang, Li Cheng
ICLR, 2025
webpage / paper / openreview / bibtex
Localized masked modeling paradigm to learn motion internal patterns from one motion with arbitrary topology.
GSD: View-Guided Gaussian Splatting Diffusion for 3D Reconstruction
Yuxuan Mu, Xinxin Zuo, Chuan Guo, Yilin Wang, Juwei Lu, Xiaofeng Wu, Songcen Xu, Peng Dai, Youliang Yan, Li Cheng
ECCV, 2024
The first 3D diffusion model directly upon Gaussian Splatting for real-world object reconstruction, with fine-grained view-guided conditioning.
RegionGrasp: A Novel Task for Contact Region Controllable Hand Grasp Generation
Yilin Wang, Chuan Guo, Li Cheng, Hai Jiang
ECCV, 2024 (Workshop)
workshop / paper / springer / bibtex
Defines a controllable hand grasp task with contact-region guidance, enabling precise contact localization in generated grasps.
Contact
Email is best: yilin32@ualberta.ca