(Bryant) Shaoheng Fang

I am an incoming Ph.D. student at the Department of Computer Science at UT Austin, advised by Qixing Huang and with the support of NSF Graduate Research Fellowship. I am broadly interested in 3D computer vision, with a recent focus on 3D/4D content generation.

Previously, I was a master's student in the Department of Computer Science at UT Austin, advised by Qixing Huang and Raymond Mooney. I received my Bachelor's degree in Computer Science from Shanghai Jiao Tong University, where I worked with Siheng Chen. I am fortunate to have worked with Chaohui Yu and Fan Wang at DAMO Academy. I am currently visiting SGP Group at UCL, advised by Niloy Mitra.

Email: bshang [at] gmail [dot] com

Email / Google Scholar / LinkedIn

News

[25/06] Honored to receive the NSF Graduate Research Fellowship!

Research

	MVRoom: Controllable 3D Indoor Scene Generation with Multi-View Diffusion Models Shaoheng Fang, Chaohui Yu, Fan Wang, Qixing Huang Under review, 2025 paper /
	Text‐Guided Interactive Scene Synthesis with Scene Prior Guidance Shaoheng Fang, Haitao Yang, Raymond Mooney, Qixing Huang EuroGraphics, 2025 paper / code /
	Self-Supervised Bird's Eye View Motion Prediction with Cross-Modality Signals Shaoheng Fang, Zuhong Liu, Mingyu Wang, Chenxin Xu, Yiqi Zhong, Siheng Chen Proceedings of the AAAI Conference on Artificial Intelligence, 2024 paper / code /
	Fedrsu: Federated learning for scene flow estimation on roadside units Shaoheng Fang, Rui Ye, Wenhao Wang, Zuhong Liu, Yuxiao Wang, Yafei Wang, Siheng Chen, Yanfeng Wang IEEE Transactions on Intelligent Transportation Systems*, 2024 paper / code /
	Aerial monocular 3d object detection Yue Hu, Shaoheng Fang, Weidi Xie, Siheng Chen IEEE Robotics and Automation Letters (RAL), 2023 paper / dataset /
	Tbp-former: Learning temporal bird's-eye-view pyramid for joint perception and prediction in vision-centric autonomous driving Shaoheng Fang, Zi Wang, Yiqi Zhong, Junhao Ge, Siheng Chen Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2023 paper /
	Where2comm: Communication-efficient collaborative perception via spatial confidence maps Yue Hu, Shaoheng Fang, Zixing Lei, Yiqi Zhong, Siheng Chen Advances in neural information processing systems, spotlight, 2022 paper / code /

Website template from here and here

(Bryant) Shaoheng Fang

News

Research

MVRoom: Controllable 3D Indoor Scene Generation with Multi-View Diffusion Models

Text‐Guided Interactive Scene Synthesis with Scene Prior Guidance

Self-Supervised Bird's Eye View Motion Prediction with Cross-Modality Signals

Fedrsu: Federated learning for scene flow estimation on roadside units

Aerial monocular 3d object detection

Tbp-former: Learning temporal bird's-eye-view pyramid for joint perception and prediction in vision-centric autonomous driving

Where2comm: Communication-efficient collaborative perception via spatial confidence maps