Weiyu Li's Homepage

About Me

I am a Ph.D. candidate at HKUST, advised by Prof. Ping Tan. Prior to this, I earned my Master's and Bachelor's degrees in 2023 and 2020 from the Interdisciplinary Research Center (IRC), Shandong University, where I was honored to be advised by Prof. Baoquan Chen. I also worked at the Visual Computing and Learning Lab (VCL-PKU) during my master period. I have been fortunate to intern at Meta AI with Prof. Andrea Vedaldi, StepFun with Xuanyang Zhang, Adobe with Dr. Tuanfeng Y. Wang, and Tencent AI Lab with Dr. Xuelin Chen.
My research focuses on 3D Content Generation, with broader interests in Point Cloud Processing, Efficient Computer Vision, and HCI with AR. I am fascinated by how we can capture, generate, and interact with the 3D world in virtual spaces. My goal is to build expressive and controllable virtual worlds with the help of AI.

News

One paper was selected as a CVPR 2026 highlight.
One paper was selected as a CVPR 2025 oral presentation.
One paper was accepted to ICLR 2024.
One paper was accepted to SIGGRAPH 2023 (TOG).
One paper was accepted to Eurographics 2022.
Won two special prizes in the Pilot Cup National University High Performance Computing Competition with RMB 200k bonus.

Publications all publications

MeshFlow: Efficient Artistic Mesh Generation via MeshVAE and Flow-based Diffusion Transformer

Weiyu Li, Antoine Toisoul, Tom Monnier, Roman Shapovalov, Rakesh Ranjan, Ping Tan, Andrea Vedaldi

CVPR 2026 Highlight [Page] [arXiv] [Paper] [Supp]

CraftsMan3D: High-Fidelity Mesh Generation with 3D Native Diffusion and Interactive Geometry Refiner

Weiyu Li^, Jiarui Liu^, Hongyu Yan^*, Rui Chen, Yixun Liang, Xuelin Chen, Ping Tan, Xiaoxiao Long

CVPR 2025 Oral [Page] [arXiv] [Paper] [Code]

Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assets

Weiyu Li, Xuanyang Zhang, Zheng Sun, Di Qi, Hao Li, Wei Cheng, Weiwei Cai, Shihao Wu, Jiarui Liu, Zihao Wang, et al.

Tech Report, 2025 [Page] [Paper] [Code] [Demo] [Model] [Dataset]

SweetDreamer: Aligning Geometric Priors in 2D Diffusion for Consistent Text-to-3D

Weiyu Li, Rui Chen, Xuelin Chen, Ping Tan

ICLR 2024 [Page] [Paper] [Code]

Example-based Motion Synthesis via Generative Motion Matching

Weiyu Li^, Xuelin Chen^†, Peizhuo Li, Olga Sorkine-Hornung, Baoquan Chen

ACM Transactions on Graphics (SIGGRAPH 2023) [Page] [Paper] [Code]
Invited to be presented at SIGGRAPH 2023 Labs Demo!

Patch-based 3D Natural Scene Generation from a Single Example

Weiyu Li^, Xuelin Chen^†, Jue Wang, Baoquan Chen

CVPR 2023 [Page] [Paper] [Code]

MoCo-Flow: Neural Motion Consensus Flow for Dynamic Humans in Stationary Monocular Cameras

Xuelin Chen, Weiyu Li, Daniel Cohen-Or, Niloy J. Mitra, Baoquan Chen

Eurographics 2022 [Page] [Paper] [Code]

Experience

Meta AI \| Research intern	London, UK
StepFun \| Research intern	Remote
Adobe \| Research intern	London, UK
Tencent AI-Lab \| Research intern	Shenzhen, China
VCL Lab, Peking University \| Visiting student	Beijing, China
AICFVE, Beijing Film Academy \| Research intern	Remote

Awards & Honors

Two Special prizes in the Pilot Cup National University High Performance Computing Competition ($30k)
The First Prize in the 12th Intel Cup Undergraduate Software Innovation Competition ($2.2k)
Two Second Prizes in Asian Student Supercomputer Challenge (ASC 2018 and 2019)
The Second Prize in China Undergraduate Mathematical Contest in Modeling
The First scholarship and titled the Superior Student in Shandong University (three times)

Miscellaneous

© Weiyu Li. All rights reserved.
Design: HTML5 UP