Scholar
Manuel Kaufmann
Google Scholar ID: 25nKBNAAAAAJ
ETH Zürich, Department of Computer Science
Citations & Impact
Citations
1,763
H-index
11
i10-index
12
Publications
18
Co-authors
27
list available
Publications
Resume (English only)
Academic Achievements
- Published 'Personalized 3D Human Body Fitting with Point Diffusion' at ICCV 2025; 'ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos' at CVPR 2025; 'EgoHDM: An Online Egocentric-Inertial Human Motion Capture, Localization, and Dense Mapping System' at SIGGRAPH Asia 2024 (TOG); and multiple papers at ECCV 2024 including 'ReLoo: Reconstructing Humans Dressed in Loose Garments from Monocular Video in the Wild' and 'WorldPose: A World Cup Dataset for Global 3D Human Pose Estimation'.
Research Experience
- Joined the Advanced Interactive Technologies lab in December 2017 as a Ph.D. student under the supervision of Prof. Otmar Hilliges.
Education
- Received MSc in Computer Science from ETH Zürich in 2017 with a thesis titled 'A Deep Learning Approach to Human Motion Sequences Infilling' supervised by Prof. Otmar Hilliges and in collaboration with vizrt Switzerland; BSc in Computer Science from the University of Basel in 2014, where his Bachelor's thesis was on 'A Statistical Shape Model of the Human Ear to Customize Hearing Devices', supervised by Prof. Thomas Vetter.
Background
- Tech lead at the ETH AI Center and a Postdoc at the AIT Lab. Interested in human-centric data acquisition pipelines, 3D human pose estimation from wearable sensors such as IMUs and electromagnetic sensors, 3D reconstruction of human avatars from images, and human motion modeling.
Miscellany
- Can also be found on LinkedIn and Google Scholar.
