Manuel Kaufmann

Manuel Kaufmann

Ph.D. student
Advanced Interactive Technologies Lab, ETH Zürich

E-Mail
manuel.kaufmann@inf.ethz.ch
Address
Stampfenbachstrasse 48, 8092 Zürich, Switzerland
Room
ETH Zurich, Department of Computer Science, STD, H 29.1


Biography

I joined the Advanced Interactive Technologies lab in December 2017 as a Ph.D. student under the supervision of Prof. Otmar Hilliges. I received my BSc in Computer Science from the University of Basel (2014) where I wrote my Bachelor thesis under the supervision of Prof. Thomas Vetter on "A Statistical Shape Model of the Human Ear to Customize Hearing Devices". I subsequently obtained a MSc in Computer Science at ETH Zürich (2017). My Master thesis was titled "A Deep Learning Approach to Human Motion Sequences Infilling" supervised by Prof. Hilliges and in collaboration with vizrt Switzerland.

In my research I focus on estimating 3D human body pose from wearable sensors (such as IMUs) to bring about full body pose in mixed reality settings. I am further generally interested in human motion modelling, for example to predict motions into the future, fill in missing frames or clean up noisy data.

You can also find me on Twitter, Linkedin, and Google scholar.



Publications

Teaser-Picture

A Spatio-temporal Transformer for 3D Human Motion Prediction

AuthorsE. Aksan, M. Kaufmann, P. Cao, O. Hilliges
In ProceedingsInternational Conference on 3D Vision (3DV), 2021
ProjectCodePDFVideoBibTeX
Teaser-Picture

EM-POSE: 3D Human Pose Estimation from Sparse Electromagnetic Trackers

AuthorsM. Kaufmann, Y. Zhao, C. Tang, L. Tao, C. Twigg, J. Song, R. Wang, O. Hilliges
In ProceedingsInternational Conference on Computer Vision (ICCV), 2021
ProjectCodePDFVideoBibTeX
Teaser-Picture

Convolutional Autoencoders for Human Motion Infilling

AuthorsM. Kaufmann, E. Aksan, J. Song, F. Pece, R. Ziegler, O. Hilliges
In Proceedings2020 International Conference on 3D Vision (3DV), 2020
ProjectCodePDFVideoBibTeX
Teaser-Picture

Structured Prediction Helps 3D Human Motion Modelling

AuthorsE. Aksan*, M. Kaufmann*, O. Hilliges
In ProceedingsThe IEEE International Conference on Computer Vision (ICCV), Oct 2019
* These two authors contributed equally to this work.
ProjectCodePDFVideoBibTeX
Teaser-Picture

Deep Inertial Poser: Learning to Reconstruct Human Pose from Sparse Inertial Measurements in Real Time

AuthorsY. Huang*, M. Kaufmann*, E. Aksan, M. Black, O. Hilliges, G. Pons-Moll
In ACM Transactions on Graphics, (Proc. SIGGRAPH Asia), Nov 2018
* These two authors contributed equally to this work.
ProjectCodePDFVideoBibTeX

Academic Activities

Student Theses

2022
MA Nina Weng Explainability in Deep Learning for Prediction of Gaze Position from EEG Data
2022
SA Yelan Tao Synthesis of Egocentric Views Showing Hand-Object Interactions
2021
MA Seok Joon Kim Conditional Hand Motion Synthesis
2020
SA Dominik Bornand Simulating Sparse Inertial Measurements for Human Pose Reconstruction
2019
BA Jonathan Lehner Real-Time Hand Tracking from Wrist-Worn RGB Cameras
2018
BA Martin Blapp Evaluation of Human Motion Models

Reviewing

2022
CVPR, ECCV, 3DV, SIGGRAPH Asia
2021
ICCV, SIGGRAPH, SIGGRAPH Asia
2020
ACM UIST, CVPR, ECCV, Eurographics, WACV
2019
Biocybernetics and Biomedical Engineering


Teaching