Hi! My name is Zekun Li (李泽坤). I am a second-year Ph.D. student in Computer Science at Brown University, working with Prof. Srinath Sridhar at Interactive 3D Vision & Learning Lab.

Before studying at Brown, I received my B. Eng. degree with honors in Computer Science at the University of Electronic Science and Technology of China (UESTC). My undergraduate research advisor is Prof. Zhao Kang. Previously, I have enriched my research experience as an intern at Tencent AI Lab and Honda Research Institute.

My research interest focuses on Generative Models and Computer Graphics. I am keen on combining knowledge-based principles and learning-based networks to achieve robust, responsible, controllable, and creative models for visual content generation. Recently, I mainly focused on character animation and human-X interaction.

I’m always open to collaboration. If you want to work with me, please contact me without hesitation! (○’◡’○)ノ

📝 Publications

ECCV2024
sym

Surf-D: High-Quality Surface Generation for Arbitrary Topologies using Diffusion Models

Zhengming Yu, Zhiyang Dou, Xiaoxiao Long, Cheng Lin, Zekun Li, Yuan Liu, Norman Müller, Taku Komura, Marc Habermann, Christian Theobalt, Xin Li, Wenping Wang
[paper] [project]

TL;DR: Design a novel UDF-based latent diffusion model for shape generation.

CVPR2024
sym

MANUS: Markerless Grasp Capture using Articulated 3D Gaussians

Chandradeep Pokhariya, Ishaan Nikhil Shah, Angela Xing, Zekun Li, Kefan Chen, Avinash Sharma, Srinath Sridhar
[paper] [project]

TL;DR: Provide a new multi-view grasping dataset with contact annotation and articulated Gaussian hand model for the benchmark.

CVPR2023
sym

Learning Anchor Transformations for 3D Garment Animation

Fang Zhao, Zekun Li, Shaoli Huang, Junwu Weng, Tianfei Zhou, Guosen Xie, Jue Wang, Ying Shan
[paper] [project]

TL;DR: Design adaptive anchors to predict 3D garment animation from a body motion sequence, especially for loose-fitting garments.

ECCV2022
sym

Eliminating Gradient Conflict in Reference-based Line-art Colorization

Zekun Li, Zhengyang Geng, Zhao Kang, Wenyu Chen, and Yibo Yang
[paper] [code]

TL;DR: Design a novel BP scheme to solve the gradient issue in Attention.

💬 Professional Service

  • Conference Reviewer: CVPR 2024, SIGGRAPH 2024, ECCV2024, AAAI 2025, ICLR 2025
  • Google explore CSR: Ph.D. mentor 2024

📖 Educations

  • 2023.09 - 2028.06 (expected), Ph.D. in Computer Science, Brown University.
  • 2019.09 - 2023.06, B. Eng. Degree in Computer Science, University of Electronic Science and Technology of China (UESTC).

💻 Internships