Haotian Zhang

I'm a Senior Research Scientist at NVIDIA Spatial Intelligence Lab (SIL). I received my Ph.D. in Computer Science from Stanford University in 2023, where I was advised by Prof. Kayvon Fatahalian. I obtained my B.E. in Computer Science and Technology from Tsinghua University in 2017, where I was advised by Prof. Shi-Min Hu.

My current research focuses on 3D human motion perception, modeling and generation. In particular, I am interested in leveraging human motion data from videos to solve problems in humanoid robotics.

Email | Google Scholar | Twitter

News

March	2026	KIMODO, a kinematic motion diffusion model is released!
March	2026	Code for GEM (GENMO) is released!
June	2025	One paper accepted to ICCV 2025.
Feb	2025	One paper accepted to Eurographics 2025.
Mar	2024	One paper accepted to ECCV 2024.
Nov	2023	Code for Learning Physically Simulated Tennis Skills from Broadcast Videos is released!
Oct	2023	Invited Talk at MIT Vision and Graphics Seminar
Oct	2023	Joined NVIDIA as a Research Scientist.
Jun	2023	Defended my Ph.D. thesis Synthesizing High-Quality and Controllable Tennis Animation From Real-World Video Collections.
Jun	2023	Invited Talk at EA Sports.
Mar	2023	Invited Talk at NVIDIA Research.
Mar	2023	Paper Learning Physically Simulated Tennis Skills from Broadcast Videos accepted to SIGGRAPH 2023 (Best Paper Honorable Mention).
Jul	2022	Paper Spotting Temporally Precise, Fine-Grained Events in Video accepted to ECCV 2022.
Jun	2022	Starting my internship at NVIDIA Toronto AI Lab.
Aug	2021	Paper Analysis of Faces in a Decade of US Cable TV News accepted to KDD 2021.
Oct	2020	Invited Talk at Facebook Reality Labs.
Oct	2020	Paper Vid2Player: Controllable Video Sprites that Behave and Appear like Professional Tennis Players accepted to TOG 2021.
July	2019	Paper An Internal Learning Approach to Video Inpainting accepted to ICCV 2019.
Mar	2019	Paper TextureNet: Consistent Local Parametrizations for Learning from High-Resolution Signals on Meshes accepted to CVPR 2019 (Oral Presentation).
Jun	2018	Starting my internship at Adobe Research.

Research

	Synthesizing High-Quality and Controllable Tennis Animation From Real-World Video Collections Haotian Zhang Ph.D. in Computer Science, Stanford University, 2023 thesis
	Kimodo: Scaling Controllable Human Motion Generation Davis Rempe, Mathis Petrovich, Ye Yuan, Haotian Zhang, Xue Bin Peng, Yifeng Jiang, Tingwu Wang, Umar Iqbal, David Minor, Michael de Ruyter, Jiefeng Li, Chen Tessler, Edy Lim, Eugene Jeong, Sam Wu, Ehsan Hassani, Michael Huang, Jin-Bey Yu, Chaeyeon Chung, Lina Song, Olivier Dionne, Jan Kautz, Simon Yuen, Sanja Fidler (*Equal Contribution) arXiv, 2026 project page \| code \| tech report
	GENMO: A GENeralist Model for Human MOtion Jiefeng Li, Jinkun Cao, Haotian Zhang, Davis Rempe, Jan Kautz, Umar Iqbal, Ye Yuan ICCV, 2025 (Highlight) project page \| code \| paper \| video \| Two Minute Papers
	HIL: Hybrid Imitation Learning of Diverse Parkour Skills from Videos Jiashun Wang, Yifeng Jiang, Haotian Zhang, Chen Tessler, Davis Rempe, Jessica Hodgins, Xue Bin Peng, arXiv, 2025 paper \| video
	Generative Motion Infilling from Imprecisely Timed Keyframes Purvi Goel, Haotian Zhang, Karen Liu, Kayvon Fatahalian Eurographics, 2025 project page \| paper \| video
	HumanoidOlympics: Sports Environments for Physically Simulated Humanoids Zhengyi Luo, Jiashun Wang, Kangni Liu, Haotian Zhang*, Chen Tessler, Jingbo Wang, Ye Yuan, Jinkun Cao Zihui Lin, Fengyi Wang, Jessica Hodgins, Kris Kitani arXiv, 2025 project page \| paper \| code
	COIN:Control-Inpainting Diffusion Prior for Human and Camera Motion Estimation Jiefeng Li, Ye Yuan, Davis Rempe, Haotian Zhang, Pavlo Molchanov, Cewu Lu, Jan Kautz, Umar Iqbal ECCV, 2024 project page \| paper
	Learning Physically Simulated Tennis Skills from Broadcast Videos Haotian Zhang, Ye Yuan, Viktor Makoviychuk, Yunrong Guo, Sanja Fidler, Xue Bin Peng, Kayvon Fatahalian SIGGRAPH, 2023 (Best Paper Honorable Mention) project page \| paper \| video \| code \| Two Minute Papers
	Spotting Temporally Precise, Fine-Grained Events in Video James Hong, Haotian Zhang, Michaël Gharbi, Matthew Fisher, Kayvon Fatahalian European Conference on Computer Vision (ECCV), 2022 project page \| paper \| code
	Vid2Player: Controllable Video Sprites that Behave and Appear like Professional Tennis Players Haotian Zhang, Cristobal Sciutto, Maneesh Agrawala, Kayvon Fatahalian ACM Transactions on Graphics (TOG), 2021 project page \| paper \| video \| Two Minute Papers
	Analysis of Faces in a Decade of US Cable TV News James Hong, Will Crichton, Haotian Zhang, Dan Fu, Jacob Ritchie, Jeremy Barenholtz, Ben Hannel, Xinwei Yao, Michaela Murray, Geraldine Moriba, Maneesh Agrawala, Kayvon Fatahalian ACM Conference on Knowledge Discovery and Data Mining (KDD), 2021 project page \| paper \| demo
	Coherent Video Generation for Multiple Hand-held Cameras with Dynamic Foreground Fang-Lue Zhang, Connelly Barnes, Haotian Zhang, Junhong Zhao, Gabriel Salas Computational Visual Media, 2020 paper
	An Internal Learning Approach to Video Inpainting Haotian Zhang, Long Mai, Ning Xu, Zhaowen Wang, John Collomosse Hailin Jin International Conference on Computer Vision (ICCV), 2019 project page \| paper \| video \| code
	TextureNet: Consistent Local Parametrizations for Learning from High-Resolution Signals on Meshes Jingwei Huang, Haotian Zhang, Li Yi, Thomas Funkhouser, Matthias Nießner Leonidas Guibas Computer Vision and Pattern Recognition (CVPR), 2019 (Oral presentation) project page \| paper \| code
	Rekall: Specifying Video Events using Compositions of Spatiotemporal Labels Dan Fu, Will Crichton, James Hong, Xinwei Yao, Haotian Zhang, Anh Truong, Avanika Narayan, Maneesh Agrawala, Christopher Ré, Kayvon Fatahalian ACM Symposium on Operating Systems Principles (SOSP), workshop on AI Systems, 2019 project page \| paper \| code
	Image-based Clothes Changing System Zhao-Heng Zheng, Haotian Zhang, Fang-Lue Zhang, Tai-Jiang Mu Computational Visual Media, 2017 paper
	Robust Background Identification for Dynamic Video Editing Fang-Lue Zhang, Xian Wu, Haotian Zhang, Jue Wang, Shi-Min Hu SIGGRAPH Asia, 2016 paper

Last updated: March, 2026

Template adapted from Ye Yuan.