profile pic

Thomas Probst

Computer Vision Lab, ETH Zürich

About Me

I am a Postdoc at the Computer Vision Lab under Prof. Luc van Gool at ETH Zürich (Switzerland). The main focus of my research is on deep learning for geometry problems, and the perception of humans for robotics.

I was working on the EurEyeCase project on robot-assisted eye surgery. I have been involved in the EU research project ReMeDi which aims to develop a system for telediagnostics.

Previously I worked on multi-modal image registration under the supervision of Christian Wojek and Heiko Neumann at Carl Zeiss Corporate Research and Technology in Oberkochen (Germany) for my masters thesis.

During my course of studies I engaged in thermal spray coating research and estimation of gas flow velocities at Daimler Research and Development in Ulm (Germany).

I took both my undergraduate and master studies in electrical engineering and computer science at Ulm University.

Publications

Conference Papers

Convex Relaxations for Consensus and Non-Minimal Problems in 3D Vision
Thomas Probst, Danda Pani Paudel, Ajad Chhatkuli, Luc Van Gool
International Conference on Computer Vision (ICCV) 2019
Seoul, South Korea [pdf]

Unsupervised Learning of Consensus Maximization for 3D Vision Problems
Thomas Probst, Danda Pani Paudel, Ajad Chhatkuli, Luc Van Gool
Computer Vision and Pattern Recognition (CVPR) 2019
Long Beach, LA, USA [code] [pdf] [poster]

What Correspondences Reveal About Unknown Camera and Motion Models?
Thomas Probst, Ajad Chhatkuli, Danda Pani Paudel, Luc Van Gool
Computer Vision and Pattern Recognition (CVPR) 2019
Long Beach, LA, USA [pdf] [poster]

Self-Supervised 3D Hand Pose Estimation Through Training by Fitting
Chengde Wan, Thomas Probst, Luc Van Gool, Angela Yao
Computer Vision and Pattern Recognition (CVPR) 2019
Long Beach, LA, USA [pdf]

Image-based Navigation using Visual Features and Map
Janine Thoma, Danda Pani Paudel, Ajad Chhatkuli, Thomas Probst, Luc Van Gool
Computer Vision and Pattern Recognition (CVPR) 2019
Long Beach, LA, USA [pdf]

Model-free Consensus Maximization for Non-Rigid Shapes
Thomas Probst, Ajad Chhatkuli, Danda Pani Paudel, Luc Van Gool
European Conference on Computer Vision (ECCV) 2018
Munich, Germany, September 2018 [pdf] [code] [poster]

Incremental Non-Rigid Structure-from-Motion with Unknown Focal Length
Thomas Probst, Danda Pani Paudel, Ajad Chhatkuli, Luc Van Gool
European Conference on Computer Vision (ECCV) 2018
Munich, Germany, September 2018 [pdf] [code] [poster] [video]

Dense 3D Regression for Hand Pose Estimation
Chengde Wan, Thomas Probst, Luc Van Gool, Angela Yao
Computer Vision and Pattern Recognition (CVPR) 2018
Salt Lake City, USA [pdf] [code]

Automatic Tool Landmark Detection for Stereo Vision in Robot-Assisted Retinal Surgery
Thomas Probst, Kevis-Kokitsi Maninis, Ajad Chhatkuli, Mouloud Ourak, Emmanuel Vander Poorten, Luc Van Gool
2018 International Conference on Robotics and Automation (ICRA) 2018
Brisbane, Australia, May 2018 [pdf] [project] [video]

Efficient Model-free Anthropometry from Depth Data
Thomas Probst, Andrea Fossati, Mathieu Salzmann and Luc Van Gool
International Conference on 3D Vision (3DV) 2017
Qingdao, China, October 2017 [pdf] [poster] [slides] [test data]

Deep Learning on Lie Groups for Skeleton-based Action Recognition
Zhiwu Huang, Chengde Wan, Thomas Probst and Luc Van Gool
Computer Vision and Pattern Recognition (CVPR) 2017
Honolulu, Hawaii, USA [pdf]

Crossing Nets: Combining GANs and VAEs with a Shared Latent Space for Hand Pose Estimation
Chengde Wan, Thomas Probst, Luc Van Gool, Angela Yao
Computer Vision and Pattern Recognition (CVPR) 2017
Honolulu, Hawaii, USA [pdf] [code]

Combining Human Body Shape And Pose Estimation For Robust Upper Body Tracking Using a Depth Sensor
Thomas Probst, Andrea Fossati and Luc Van Gool
Fourth International Workshop on Assistive Computer Vision and Robotics (ACVR) 2016
Amsterdam, The Netherlands, October 2016 [pdf]

Pre-prints and Workshop Papers

Dual Grid Net: hand mesh vertex regression from single depth maps
Chengde Wan, Thomas Probst, Luc Van Gool, Angela Yao
[pdf]

Learning Feature Representations for Look-Alike Images
Ayca Takmaz , Thomas Probst, Danda Pani Paudel, Luc Van Gool
Vision Meets Cogntition Workshop at Computer Vision and Pattern Recognition (CVPR) 2019
Long Beach, LA, USA [pdf] [poster]

Toward Global Calibration of a Robot-Assisted Vitreo-Retinal Surgery based on OCT C-Scan Image Registration
Mouloud Ourak, Gianni Borghesan, Laure Esteveny, Simon Hecker, Thomas Probst, Ajad Chhatkuli, Kevis Kokitsi Maninis, Eva Lankenau, Hinnerk Schulz-Hildebrandt, Dominiek Reynaerts and Emmanuel B. Vander Poorten
Proceedings of the 7th Joint Workshop on New Technologies for Computer/Robot Assisted Surgery
Montpellier, France, September 2017

Deeply Learned 2D Tool Pose Estimation for Robot-to-Camera Registration
Kevis-Kokitsi Maninis, Ajad Chhatkuli, Jordi Pont-Tuset, Simon Hecker, Thomas Probst, Mouloud Ourak, Emmanuel Vander Poorten and Luc Van Gool
Proceedings of the 7th Joint Workshop on New Technologies for Computer/Robot Assisted Surgery
Montpellier, France, September 2017

Online Reconstruction of Retinal 3D Maps from Stereo in Close-to-Realtime for Eye Surgery
Simon Hecker, Thomas Probst, Ajad Chhatkuli, Kevis-Kokitsi Maninis, Michal Havlena, Emmanuel Vander Poorten and Luc Van Gool
Proceedings of the 7th Joint Workshop on New Technologies for Computer/Robot Assisted Surgery
Montpellier, France, September 2017

Automated Visual Input Analysis for a Telediagnostic Robot System
Thomas Probst, Andrea Fossati and Luc Van Gool
Proceedings of the 5th Joint Workshop on New Technologies for Computer/Robot Assisted Surgery
Brussels, Belgium, September 2015 [pdf]

Other

Vision Meets Telediagnostic Robotics
Thomas Probst, Andrea Fossati and Luc Van Gool
International Computer Vision Summer School (ICVSS) 2016
Sicily, July 2016 [pdf poster]

Learning Based Multi-Modal Image Registration
Thomas Probst, Christian Wojek, Heiko Neumann
Masters Thesis
Ulm University and Carl Zeiss Corporate Research, 2014 [pdf]

Code

NRSfM Toolbox
A unified MATLAB toolbox for non-rigid shape-from-motion methods.
[code]

Model-free Consensus Maximization for Non-rigid Shapes
A basic implementation of the isometric shape matching algorithm as presented in the paper.
[code]

Unsupervised Learning of Consensus Maximization for 3D Vision Problems
A basic implementation of unsupervised fundamental matrix estimation.
[code]

Contact Me

Feel free to contact me via mail:

probstt@vision.ee.ethz.ch