Homepage - Zeyu Hu

Zeyu Hu (胡泽宇)

Senior Researcher · LightSpeed Studios Singapore

A senior researcher at LightSpeed Studios Singapore, feel free to reach out.

I obtained my Ph.D. degree (2018-2023) at the Vision and Graphics Group, part of the Department of Computer Science and Engineering at the Hong Kong University of Science and Technology. My Ph.D. advisor was Prof. Chiew-Lan Tai, and I also worked closely with Prof. Long Quan and Prof. Hongbo Fu.

Before joining HKUST, I received a Bachelor's degree in Automation from the University of Science and Technology of China in 2018.

Working on game related AI research and development now.

zhuam(at)connect.ust.hk CV

Experience

LightSpeed Studios, China
Research Intern
Aug. 2020 - Jan. 2023

LightSpeed Studios, Singapore
Senior Researcher
Mar. 2023 - Present

Education

Hong Kong University of Science and Technology
Ph.D. in Computer Science and Engineering
Sep. 2018 - Jul. 2023

University of Science and Technology of China
B.S. in Automation
Sep. 2014 - Jul. 2018

Selected Publications

View All Publications

3D Generative AI

LumiTex: Towards High-Fidelity PBR Texture Generation wit Illumination Context

Jingzhi Bao, Hongze Chen, Lingting Zhu, Chenyu Liu, Runze Zhang, Keyang Luo, Zeyu Hu, Weikai Chen, Yingda Yin, Xin Wang, Zehong Lin, Jun Zhang, Xiaoguang Han

ICLR 2026

[Paper] [Code] [Project]

LumiTex: Towards High-Fidelity PBR Texture Generation wit Illumination Context

Jingzhi Bao, Hongze Chen, Lingting Zhu, Chenyu Liu, Runze Zhang, Keyang Luo, Zeyu Hu, Weikai Chen, Yingda Yin, Xin Wang, Zehong Lin, Jun Zhang, Xiaoguang Han

ICLR 2026

[Paper] [Code] [Project]

Light-SQ: Structure-aware Shape Abstraction with Superquadrics for Generated Meshes

Yuhan Wang, Weikai Chen, Zeyu Hu, Runze Zhang, Yingda Yin, Ruoyu Wu, Keyang Luo, Shengju Qian, Yiyan Ma, Hongyi Li, Yuan Gao, Yuhuan Zhou, Hao Luo, Wan Wang, Xiaobin Shen, Zhaowei Li, Kuixin Zhu, Chuanlang Hong, Yueyue Wang, Lijie Feng, Xin Wang, Chen Change Loy

SIGGRAPH Asia 2025

Selected Publications

3D Generative AI

LumiTex: Towards High-Fidelity PBR Texture Generation wit Illumination Context

LumiTex: Towards High-Fidelity PBR Texture Generation wit Illumination Context

Light-SQ: Structure-aware Shape Abstraction with Superquadrics for Generated Meshes

Light-SQ: Structure-aware Shape Abstraction with Superquadrics for Generated Meshes

MAR-3D: Progressive Masked Auto-regressor for High-Resolution 3D Generation

MAR-3D: Progressive Masked Auto-regressor for High-Resolution 3D Generation

Motion Generative AI

MotionLab: Unified Human Motion Generation and Editing via the Motion-Condition-Motion Paradigm

MotionLab: Unified Human Motion Generation and Editing via the Motion-Condition-Motion Paradigm

Off-the-shelf ChatGPT is a Good Few-shot Human Motion Predictor

Off-the-shelf ChatGPT is a Good Few-shot Human Motion Predictor

3D Scene Understanding

LiDAL: Inter-frame Uncertainty Based Active Learning for 3D LiDAR Semantic Segmentation

LiDAL: Inter-frame Uncertainty Based Active Learning for 3D LiDAR Semantic Segmentation

TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers

TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers

VMNet: Voxel-Mesh Network for Geodesic-Aware 3D Semantic Segmentation

VMNet: Voxel-Mesh Network for Geodesic-Aware 3D Semantic Segmentation

3D Scene Reconstruction

Learning to Match Features with Seeded Graph Matching Network

Learning to Match Features with Seeded Graph Matching Network

PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency

PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency