Bios

My name is Hongchi Xia (夏鸿驰). I’m now a second-year Ph.D. student at Computer Science at University of Illinois Urbana-Champaign (UIUC), where I collaborate with Shenlong Wang and Wei-Chiu Ma.

My research lies in 3D computer vision, building essential foundations for spatial intelligence. Previously, I conducted a series of works related to 3D reconstruction and photorealistic re-simulation with grounded physics. Recently, I’ve gone into 3D generation approach, aiming at addressing the urgent need of rich and diverse 3D data.

I received my bachelor’s degree at Shanghai Jiao Tong University (SJTU), and I was fortunate to have research internships advised by Shenlong Wang at UIUC, Wei-Chiu Ma at Cornell, Xiaolong Wang at UCSD and Cewu Lu at SJTU. I was a research intern at NVIDIA Deep Imagination Research during Summer 2025, where I mainly collaborated with Fangyin Wei.

Check my Curriculum Vitae Here.

News

• Feb.2026 Our new agentic scene generation project “SAGE” is released!
• Oct.2025 “HoloScene” is accepted to NeurIPS 2025! See you in San Diego!
• May.2025 Had my first summer internship at NVIDIA.
• Apr.2025 “DRAWER” is accepted to CVPR 2025! See you in Nashville!
• Aug.2024 Start the PhD journey at UIUC!
• Feb.2024 Two papers “Video2Game” and “WildRGB-D” are accepted to CVPR 2024!

Selected Publications [ALL]

SAGE: Scalable Agentic 3D Scene Generation for Embodied AI

Hongchi Xia, Xuan Li, Zhaoshuo Li, Qianli Ma, Jiashu Xu, Ming-Yu Liu, Yin Cui, Tsung-Yi Lin, Wei-Chiu Ma, Shenlong Wang, Shuran Song, Fangyin Wei

Arxiv

[project] [paper] [code] [dataset]

HoloScene: Simulation-Ready Interactive 3D Worlds from a Single Video

Hongchi Xia, Chih-Hao Lin, Hao-Yu Hsu, Quentin Leboutet, Katelyn Gao, Michael Paulitsch, Benjamin Ummenhofer, Shenlong Wang

Neural Information Processing Systems (NeurIPS), 2025

[project] [paper] [code]

DRAWER: Digital Reconstruction and Articulation With Environment Realism

Hongchi Xia, Entong Su, Marius Memmel, Arhan Jain, Raymond Yu, Numfor Mbiziwo-Tiapo, Ali Farhadi, Abhishek Gupta, Shenlong Wang, Wei-Chiu Ma

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025

[project] [paper] [code]

Video2Game: Real-time, Interactive, Realistic and Browser-Compatible Environment from a Single Video

Hongchi Xia, Zhi-Hao Lin, Wei-Chiu Ma, Shenlong Wang

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024

[project] [paper] [code]

RGBD Objects in the Wild: Scaling Real-World 3D Object Learning from RGB-D Videos

Hongchi Xia*, Yang Fu*, Sifei Liu, Xiaolong Wang

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024

[project] [paper] [code]