Xinyue Wei

About

I am a research scientist and tech lead at Hillbot Inc. I obtained my Ph.D. degree in ECE at UC San Diego in 2025, advised by Prof. Hao Su. Before that, I received my B.E. degree in computer science and technology from Tongji University in 2020. My research interests are in Computer Graphics, Computer Vision and Embodied AI.

News

Aug 2025 Three papers accepted by SIGGRAPH Asia 2025, one paper accepted by Pacific Graphics 2025!

Jun 2025 I joined Hillbot as a research scientist.

Jun 2025 I was selected as an Outstanding Reviewer by CVPR 2025.

May 2025 I successfully defended my Ph.D. thesis!

Sep 2024 One paper accepted by NeurIPS 2024.

May 2024 I was selected for the WiGRAPH Rising Stars program.

Feb 2024 Two papers accepted by CVPR 2024.

Publications and preprints

FreeArt3D: Training-Free Articulated Object Generation using 3D Diffusion

Chuhao Chen, Isabella Liu, Xinyue Wei, Hao Su, Minghua Liu

SIGGRAPH Asia 2025 (Conference Track)

PDF Code Demo Project Bibtex

LARM: A Large Articulated Object Reconstruction Model

Sylvia Yuan, Ruoxi Shi, Xinyue Wei, Xiaoshuai Zhang, Hao Su, Minghua Liu

SIGGRAPH Asia 2025 (Conference Track)

PDF Code Project Bibtex

PartUV: Part-Based UV Unwrapping of 3D Meshes

Zhaoning Wang, Xinyue Wei, Ruoxi Shi, Xiaoshuai Zhang, Hao Su, Minghua Liu

SIGGRAPH Asia 2025 (Conference Track)

PDF Code Project Bibtex

PaMO: Parallel Mesh Optimization for Intersection-Free Low-Poly Modeling on the GPU

Seonghun Oh*, Xiaodi Yuan*, Xinyue Wei*, Ruoxi Shi, Fanbo Xiang, Minghua Liu, Hao Su

Pacific Graphics 2025 (Journal Track)

PDF Code Project Bibtex

Cosmos: World Foundation Model Platform for Physical AI

Core Contributor (77 authors)

White Paper

PDF Product Project Bibtex

MeshFormer: High-Quality Mesh Generation with 3D-Guided Reconstruction Model

Minghua Liu*, Chong Zeng*, Xinyue Wei, Ruoxi Shi, Linghao Chen, Chao Xu, Mengqi Zhang, Zhaoning Wang, Xiaoshuai Zhang, Isabella Liu, Hongzhi Wu, Hao Su

NeurIPS 2024 (Oral)

PDF Demo Project Bibtex

MeshLRM: Large Reconstruction Model for High-Quality Meshes

Xinyue Wei*, Kai Zhang*, Sai Bi, Hao Tan, Fujun Luan, Valentin Deschaintre, Kalyan Sunkavalli, Hao Su, Zexiang Xu

Technical Report

PDF Demo Project Bibtex

ZeroRF: Fast Sparse View 360° Reconstruction with Zero Pretraining

Ruoxi Shi*, Xinyue Wei*, Cheng Wang, Hao Su

CVPR 2024

PDF Code Project Bibtex

One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion

Minghua Liu*, Ruoxi Shi*, Linghao Chen*, Zhuoyang Zhang*, Chao Xu*, Xinyue Wei, Hansheng Chen, Chong Zeng, Jiayuan Gu, Hao Su

CVPR 2024

PDF Demo Project Bibtex

Zero123++: A Single Image to Consistent Multi-view Diffusion Base Model

Ruoxi Shi, Hansheng Chen, Zhuoyang Zhang, Minghua Liu, Chao Xu, Xinyue Wei, Linghao Chen, Chong Zeng, Hao Su

Technical Report

PDF Code Demo Bibtex

NeuManifold: Neural Watertight Manifold Reconstruction with Efficient and High-Quality Rendering Support

Xinyue Wei, Fanbo Xiang, Sai Bi, Anpei Chen, Kalyan Sunkavalli, Zexiang Xu*, Hao Su*

WACV 2025 (Oral)

PDF Code Project Bibtex

Dictionary Fields: Learning a Neural Basis Decomposition

Anpei Chen, Zexiang Xu, Xinyue Wei, Siyu Tang, Hao Su, Andreas Geiger

SIGGRAPH 2023 (Journal Track)

PDF Code Project Bibtex

ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills

Jiayuan Gu*, Fanbo Xiang*, Xuanlin Li+, Zhan Ling+, Xiqiang Liu+, Tongzhou Mu+, Yihe Tang+, Stone Tao+, Xinyue Wei+, Yunchao Yao+, Xiaodi Yuan, Pengwei Xie, Zhiao Huang, Rui Chen, Hao Su

ICLR 2023

PDF Code Project Bibtex

Approximate Convex Decomposition for 3D Meshes with Collision-Aware Concavity and Tree Search

Xinyue Wei*, Minghua Liu*, Zhan Ling, Hao Su

SIGGRAPH 2022 (Journal track)

PDF Code Project Bibtex

End-to-End Adaptive Monte Carlo Denoising and Super-Resolution

Xinyue Wei, Haozhi Huang, Yujin Shi, Hongliang Yuan, Li Shen, Jue Wang

Arxiv 2021

PDF Bibtex

Experience

Research Scientist at Hillbot (sudoAI), June 2025 - Present

Research Intern at Hillbot (sudoAI), Jan 2025 - June 2025

Research Intern at NVIDIA, Oct 2024 - Jan 2025

World foundation models

Research Intern at Hillbot (sudoAI), Mar 2024 - Oct 2024

3D mesh generation

Research Intern at Adobe, Oct 2023 - Mar 2024

3D reconstruction

Research Intern, GILL Group at Adobe, Jun 2022 - Mar 2023

Neural surface reconstruction

Research Intern, AI Graphics Group at Tencent AI Lab, Mar 2020 - Feb 2021

Monte Carlo denoising

Research Intern, CCVL Lab at Johns Hopkins University, Jul 2019 - Oct 2019

Computer vision

Services

Reviewer for SIGGRAPH '22 '25, SIGGRAPH Asia '23 '25, CVPR '22 '23 '24 '25, ECCV '22 '24, ICCV '23 '25, 3DV '23, ICRA '23 '24, WACV '25, IEEE CGA

Misc.

I like photography, cooking, singing, piano, and acrylic marker painting.