Prof. Dr. Torsten Schön

Prof. Dr. Torsten Schön
Room: K201
Subject Area: Computer Vision for Intelligent Mobility Systems
Faculty: Fakultät I
  • Since 2020 Reserach professor at THI
  • 2014-2020: Audi AG: Senior Data Scientist for Artificial Intelligence
  • 2013-2014: dotplot GmbH and Clueda AG: Data Scientist
  • 2013-2014: FHM Bamberg: Lecturer for descriptive and inductive statistics
  • 2011-2013: SustSol GmbH: PhD student and software engineer
  • 2011-2013: Universität Regensburg: PhD Student in the Machine Learning group
  • 2010-2013: Softgate GmbH: Software Developer
  • 2008-2013: Self employed: Webdesign and -programming
  • 2005-2010 Hochschule Weihenstephan-Triesdorf: Diploma study of Bioinformatics
  • Predicting Driver Behavior on the Highway with Multi-Agent Adversarial Inverse Reinforcement Learning, H Radtke, H Bey, M Sackmann, T Schön - 2023 IEEE Intelligent Vehicles Symposium (IV), 2023
  • Rößle Dominik, Prey Lukas, Ramgraber Ludwig, Hanemann Anja, Cremers Daniel, Noack Patrick Ole, Schön Torsten. Efficient Noninvasive FHB Estimation using RGB Images from a Novel Multiyear, Multirater Dataset. Plant Phenomics. 2023:5;0068. DOI:10.34133/plantphenomics.0068
  • C. de Andrade, M.; Nogueira, M.; Fidelis, E.; Campos, L.; Campos, P.; Schön, T. and de Abreu Faria, L. (2023). Exploiting GAN Capacity to Generate Synthetic Automotive Radar Data. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP
  • B. J. Souza et al., "AImotion Challenge Results: a Framework for AirSim Autonomous Vehicles and Motion Replication," 2022 2nd International Conference on Computers and Automation (CompAuto), Paris, France, 2022, pp. 42-47, doi: 10.1109/CompAuto55930.2022.00015.
  • D Rößle, D Cremers, T Schön. "Perceiver Hopfield Pooling for Dynamic Multi-modal and Multi-instance Fusion", International Conference on Artificial Neural Networks (2022), 599-610
  • H Schieber, F Duerr, T Schoen, J Beyerer. "Deep Sensor Fusion with Pyramid Fusion Networks for 3D Semantic Segmentation", IEEE Intelligent Vehicles Symposium (IV) (IV 2022), Aachen, Germany
  • T. Schön, Artificial Intelligence Inspired by Human Learning, Book chapter in AI.Mobility.Science, ISBN 978-3-00-071542-6 (2022)
  • F Leinen, V Cozzolino, T Schön. "VolNet: Estimating Human Body Part Volumes from a Single RGB Image", arXiv preprint arXiv:2107.02259 (2021)
  • T Balaji, P Blies, G Göri, R Mitsch, M Wasserer, T Schön. "Temporally coherent video anonymization through GAN inpainting", arXiv preprint arXiv:2106.02328 (2021)
  • Patrick Wenzel, Torsten Schön, Laura Leal-Taixé, and Daniel Cremers. „Vision-Based Mobile Robotics Obstacle Avoidance With Deep Reinforcement Learning”. In: IEEE International Conference on Robotics and Automation (ICRA), 2021. DOI:10.1109/ICRA48506.2021.9560787
  • Torsten Schön, Martin Stetter, Elmar W. Lang, Physarum Learner: A bio-inspired way of learning structure from data, Expert Systems With Applications, 2014
  • Torsten Schön, Martin Stetter, Elmar W. Lang, A new Physarum Learner for Network Structure Learning from Biomedical Data, Proceedings of the 6th International Conference in Bio-inspired Systems and Signal Processing BIOSIGNALS 2013, February 11-14, Barcelona, Spain
  • Torsten Schön, Martin Stetter, Elmar W. Lang, Structure Learning for Bayesian Networks using the Physarum Solver, Proceedings of the 11th International Conference on Machine Learning and Applications ICMLA 2012, December 12-15, Boca Raton, Florida, USA
  • Torsten Schön , Alexey Tsymbal , Martin Huber, Gene-pair representation and incorporation of GO-based semantic similarity into classification of gene expression data, Intelligent Data Analysis 2012
  • Torsten Schön , Alexey Tsymbal , Martin Huber, Gene-Pair Representation and Incorporation of GO-based Semantic Similarity into Classification of Gene Expression Data, Proceedings of the 7th international conference on Rough sets and current trends in computing, June 28-30, 2010, Warsaw, Poland

Computer Vision for Intelligent Mobility Systems

The Computer Vision for Intelligent Mobility Systems research group is concerned with deep learning methods for analysing and generating image data. Data from different imaging sensors in two- and three-dimensional space are processed. The aim of the research group is to develop super-human perception for automated vehicles, aircraft, rail vehicles and other means of transport, and to analyse image data from infrastructure sensors for traffic monitoring.
In addition to the efforts in the mobility sector, the research group is committed to the use of computer vision for improved environmental protection and more sustainability.



Former Lectures:


Executive Education:


Open Positions

You are interested in computer vision and my research group? Feel free to contact me for currently open positions!


Scientific staff

Unfortunately, there are no open positions at this time.

Bachelor or Master thesis

Your thesis in on one hand the conclusion of your Education, but on the other hand it also the start into your professional career!

Take the chance to use your thesis to dive into one of the most attractive future technology: Artificial Intelligence!

I offer different topics within the field of computer vision, especially in deep learning, with applications for intelligent mobility systems. I can either offer attractive topics from within my research group or get you in touch with interesting contact from the industry.

Open positions at moodle

Interested but no suitable thesis description online? Feel free to drop me an e-mail!


Student assistance jobs

Unfortunately, there are no open positions at this time.

Members of the research group

PhD Student
Dominik Rößle
Phone: +49 841 9348-6603
PhD student (extern)
Muhammad Saad Nawaz
Luca Schreiber
Phone: +49 841 9348-2851
Room: P107
PhD student
Daniel Kriegl
Phone: +49 841 9348-2349