Xiangjun Gao

Xiangjun GAO (高祥君)

I am a third year PhD candidate at (HKUST), supervised by Prof. Long Quan. Previously, I obtained my Master's and Bachelor's degrees in Computer Science from Beijing Institute of Technology (BIT). I am expected to graduate in 2027.

My research focuses on 3D Vision, including Avatar, 3D-Aware Video Model, and 3D LLM. Previously, I interned at Microsoft Research, ByteDance , Tencent AI Lab and ARC Lab.

Google Scholar / Twitter / Github / Email: xgaobq@connect.ust.hk

Preprints

Complex-Valued 2D Gaussian Representation for Computer-Generated Holography
Yicheng Zhan*, Xiangjun Gao*, Long Quan, Kaan Aksit
arXiv, 2026. (*: Co-first authorship).

arXiv

StereoCrafter: Diffusion-based Generation of Long and High-fidelity Stereoscopic from Monocular Videos
Sijie Zhao, Wenbo Hu, Xiaodong Cun, Yong Zhang, Xiaoyu Li, Zhe Kong, Xiangjun Gao, Muyao Niu, Ying Shan
Arxiv, 2024.

Project page

Code

arXiv

Publications

Map2Thought: Explicit 3D Spatial Reasoning via Metric Cognitive Maps
Xiangjun Gao, Zhensong Zhang, Dave Zhenyu Chen, Songcen Xu, Long Quan, Eduardo Pérez-Pellitero, Youngkyoon Jang
CVPR, 2026, Findings

arXiv

Longsplat: Online Generalizable 3D Gaussian Splatting from Long Sequence Images
Guichen Huang, Ruoyu Wang, Xiangjun Gao, Che Sun, Yuwei Wu, Shenghua Gao, Yunde Jia
AAAI, 2026.

arXiv

ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis
Wangbo Yu, Jinbo Xing, Li Yuan, Wenbo Hu, Xiaoyu Li, Z. Huang, Xiangjun Gao, Tien-Tsin Wong, Ying Shan, Yonghong Tian
TPAMI, 2025

Project page

Code

arXiv

GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors
Tian-Xing Xu, Xiangjun Gao, Wenbo Hu, Xiaoyu Li, Song-Hai Zhang, Ying Shan
ICCV, 2025.

Project page

Code

arXiv

Mani-GS: Gaussian Splatting Manipulation with Triangular Mesh
Xiangjun Gao, Xiaoyu Li, Yiyu Zhuang, Qi Zhang, Wenbo Hu, Chaopeng Zhang, Yao Yao, Ying Shan, Long Quan
CVPR, 2025.

Project page

Code

arXiv

DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos
Wenbo Hu*, Xiangjun Gao*, Xiaoyu Li*, Sijie Zhao, Xiaodong Cun,Yong Zhang, Long Quan, Ying Shan
CVPR, 2025. (*: equal contribution). (Highlight). (Also Best Paper Award of PixFoundation workshop).

Project page

Code

arXiv

MagicMan: Generative Novel View Synthesis of Humans with 3D-Aware Diffusion and Refinement
Xu He, Xiaoyu Li, Di Kang, Jiangnan Ye, Chaopeng Zhang, L. Chen, Xiangjun Gao, Han Zhang, Zhiyong Wu, Haolin Zhuang
AAAI, 2025.

Project page

Code

arXiv

HiFi-123: Towards High-fidelity One Image to 3D Content Generation
Wangbo Yu, Li Yuan, Yan-Pei Cao, Xiangjun Gao, Xiaoyu Li, Wenbo Hu, Long Quan, Ying Shan, Yonghong Tian
ECCV, 2024

Project page

Code

arXiv

ConTex-Human: Free-View Human Rendering from Single Image with Texture-Consistent Synthesis
Xiangjun Gao, Xiaoyu Li, Chaopeng Zhang, Qi Zhang, Yanpei Cao, Ying Shan, Long Quan
CVPR, 2024

Project page

Code

arXiv

MPS-NeRF: Generalizable 3D Human Rendering from Multiview Images
Xiangjun Gao, Jiaolong Yang, Jongyoo Kim, Sida Peng, Zicheng Liu, and Xin Tong
TPAMI, 2022

Project page

Code

arXiv

Experience

During my studies, I had the opportunity to work as a research intern at:

Microsoft Research Asia (2021) (advised by Dr. Jiaolong Yang and Dr. Xin Tong)
ByteDance (2022) (advised by Dr. Jiashi Feng)
Tencent AI Lab (2023) → ARC Lab (2024) (advised by Dr. Xiaoyu Li and Dr. Wenbo Hu)
London Reseach Center of Huawei (2025) (advised by Dr. Zhensong Zhang, Youngkyoon Jang, and Eduardo Pérez-Pellitero)

Academic Services

Serve as conference reviewer for CVPR, ECCV, ICLR, AAAI, Siggraph, WACV, CGI.
Serve as journal reviewer for TVCG, TIP, TMM.

Last updated in February 2026. Template adapted from Siwei Zhang's and Qianli Ma's websites.