Jian Wang

I am a researcher at Meta. My research focuses on computer vision, computer graphics, and deep learning, with an emphasis on egocentric human motion capture, human motion generation and understanding, full-body avatars, and human performance capture.

I received my Ph.D. in Computer Science from the Max Planck Institute for Informatics and Saarland University, advised by Christian Theobalt. Before that, I earned an M.Eng. in Computer Science from the Institute of Software, Chinese Academy of Sciences, and a B.Sc. in Chemistry from Peking University.

Email / LinkedIn / GitHub / Twitter / MPI-INF page

Research

My work develops perception and generation methods for people-centric 3D understanding. Recent projects study egocentric sensing, whole-body motion capture, multi-modal human motion understanding, and avatar reconstruction from challenging first-person inputs.

News

2025 Invited talk at the ICCV 2025 EgoMotion Workshop.
2025 Ego4o and FRAME appeared at CVPR 2025.
2025 Bring Your Rear Cameras for Egocentric 3D Human Pose Estimation appeared at ICCV 2025.
2024 EgoAvatar appeared at SIGGRAPH Asia 2024, and several egocentric capture papers appeared at CVPR 2024.

Publications

	Ego4o: Egocentric Human Motion Capture and Understanding from Multi-Modal Input Jian Wang, R. Dabral, D. Luvizon, Z. Cao, L. Liu, T. Beeler, C. Theobalt CVPR 2025 Proceedings of the Computer Vision and Pattern Recognition Conference. PDF / Project / ArXiv
	FRAME: Floor-aligned Representation for Avatar Motion from Egocentric Video A. B. Camiletto, Jian Wang, E. Alvarado, R. Dabral, T. Beeler, M. Habermann, C. Theobalt CVPR 2025 Proceedings of the Computer Vision and Pattern Recognition Conference. PDF / Project / ArXiv
	Bring Your Rear Cameras for Egocentric 3D Human Pose Estimation H. Akada, Jian Wang, V. Golyanik, C. Theobalt ICCV 2025 Proceedings of the IEEE/CVF International Conference on Computer Vision. PDF / Project / Code
	Egocentric Whole-Body Motion Capture with FisheyeViT and Diffusion-Based Motion Refinement Jian Wang, Z. Cao, D. Luvizon, L. Liu, K. Sarkar, D. Tang, T. Beeler, C. Theobalt CVPR 2024 Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. PDF / Project / ArXiv
	EgoAvatar: Egocentric View-Driven and Photorealistic Full-Body Avatars J. Chen, Jian Wang, Y. Zhang, R. Pandey, T. Beeler, M. Habermann, C. Theobalt SIGGRAPH Asia 2024 Conference Papers. PDF / Project / ArXiv
	3D Human Pose Perception from Egocentric Stereo Videos H. Akada, Jian Wang, V. Golyanik, C. Theobalt CVPR 2024 Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. PDF / Project / Code
	EventEgo3D: 3D Human Motion Capture from Egocentric Event Streams C. Millerdurai, H. Akada, Jian Wang, D. Luvizon, C. Theobalt, V. Golyanik CVPR 2024 Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. PDF / Project / Code
	Scene-Aware Egocentric 3D Human Pose Estimation Jian Wang, D. Luvizon, W. Xu, L. Liu, K. Sarkar, C. Theobalt CVPR 2023 Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. PDF / Project / Code / ArXiv
	UnrealEgo: A New Dataset for Robust Egocentric 3D Human Motion Capture H. Akada, Jian Wang, S. Shimada, M. Takahashi, C. Theobalt, V. Golyanik ECCV 2022 European Conference on Computer Vision. PDF / Project / Code
	Estimating Egocentric 3D Human Pose in the Wild with External Weak Supervision Jian Wang, L. Liu, W. Xu, K. Sarkar, D. Luvizon, C. Theobalt CVPR 2022 Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. PDF / Project / ArXiv
	Estimating Egocentric 3D Human Pose in Global Space Jian Wang, L. Liu, W. Xu, K. Sarkar, C. Theobalt ICCV 2021 (Oral) Proceedings of the IEEE/CVF International Conference on Computer Vision. PDF / Project / ArXiv
	From Model to Implementation: A Network Algorithm Programming Language Jian Wang, J. An, M. Chen, N. Zhan, L. Wang, M. Zhang, T. Gan SCIS 2020 Science China Information Sciences. PDF / Project
	Re-Identification Supervised Texture Generation Jian Wang, Y. Zhong, Y. Li, C. Zhang, Y. Wei CVPR 2019 Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. PDF / Project / ArXiv
	NIL: Learning Nonlinear Interpolants M. Chen, Jian Wang, J. An, B. Zhan, D. Kapur, N. Zhan CADE 2019 International Conference on Automated Deduction. PDF / Project / ArXiv

Education

Ph.D. in Computer Science, Max Planck Institute for Informatics and Saarland University, 2020-2024.
M.Eng. in Computer Science, Institute of Software, Chinese Academy of Sciences, 2016-2019.
B.Sc. in Chemistry, Peking University, 2012-2016.

Experience

Researcher, Meta.
Research Intern, Max Planck Institute for Informatics, 2019-2020.
Research Intern, Megvii Inc., 2018.
Research Intern, Institute of Automation, Chinese Academy of Sciences, 2018.
Research Intern, Baidu Inc., 2017.