My current research topic is the similarity assessment of data from numerical PDE simulations. In short, common comparison operations for this data like L¹ or L² metrics are suboptimal, as the only consider local distances without accounting for the context or larger structures. I’m investigating deep learning methods to create more accurate and robust comparison models for this task. In addition, I’m interested in more general topics in physics-based simulations, machine learning, computer graphics, and game development.
I’m a Ph.D. student in Nils Thuerey’s group since November 2019. I received my M.Sc. and B.Sc degrees in Informatics: Games Engineering at the Technical University of Munich as well.
E-mail: georg.kohl (at) tum.de
- Georg Kohl, Li-Wei Chen, and Nils Thuerey, “Learning Similarity Metrics for Volumetric Simulations with Multiscale CNNs“, arXiv, 2022 [Project]
- Georg Kohl, Kiwon Um, and Nils Thuerey, “Learning Similarity Metrics for Numerical Simulations“, International Conference on Machine Learning, 2020 [Project]
- Georg Kohl, “Accuracy Evaluation of Numerical Simulation Methods with CNNs“, M.Sc. Thesis, Technical University of Munich, October 2019. (English)
- Georg Kohl, “Visual Enhancement of Liquid Simulations using Secondary Particles“, B.Sc. Thesis, Technical University of Munich, September 2017. (English) [Video]
- Summer 2022: Computer Games Laboratory
- Summer 2021: Grundlagen: Algorithmen und Datenstrukturen
- Winter 2020/21: Seminar – Deep Learning in Computer Graphics
- Summer 2020: Computer Games Laboratory
- Hanfeng Wu, “Perceptual Losses for Deep Learning on Fluid Simulations”, B.Sc. Thesis, TUM, September 2021
- Benjamin Holzschuh, “Transfer Learning for Physical Simulations”, M.Sc. Thesis, TUM, March 2021