Jakob Kruse

Doctoral student at Visual Learning Lab Heidelberg
Mathematikon B, room A117

Email: jakob.kruse (at) iwr.uni-heidelberg.de
Phone: +49 6221 54 14887 (shared)
IWR, Uni Heidelberg
Berliner Straße 43
69120 Heidelberg


Lynton Ardizzone, Carsten Lüth, Jakob Kruse, Carsten Rother, Ullrich Köthe. Guided Image Generation with Conditional Invertible Neural Networks. arXiv:1907.02392, July 2019.
[arXiv page]

Jakob Kruse, Lynton Ardizzone, Carsten Rother, Ullrich Köthe. Benchmarking Invertible Architectures on Inverse Problems. First Workshop on Invertible Neural Networks and Normalizing Flows (ICML 2019), Long Beach, USA, June 2019.
[Paper] [Poster]

Tim J Adler, Lynton Ardizzone, Anant Vemuri, Leonardo Ayala, Janek Gröhl, Thomas Kirchner, Sebastian Wirkert, Jakob Kruse, Carsten Rother, Ullrich Köthe, Lena Maier-Hein. Uncertainty-Aware Performance Assessment of Optical Imaging Modalities with Invertible Neural Networks. International Journal of Computer Assisted Radiology and Surgery (IJCARS), 14:997, June 2019.

Lynton Ardizzone, Jakob Kruse, Sebastian Wirkert, Daniel Rahner, Eric W. Pellegrini, Ralf S. Klessen, Lena Maier-Hein, Carsten Rother, Ullrich Köthe. Analyzing Inverse Problems with Invertible Neural Networks. International Conference on Learning Representations (ICLR), New Orleans, USA, May 2019.
[OpenReview page] [Poster] [Code]

Jakob Kruse, Carsten Rother and Uwe Schmidt. Learning to Push the Limits of Efficient FFT-based Image Deconvolution. IEEE International Conference on Computer Vision (ICCV), Venice, Italy, October 2017.
Spotlight presentation.
[Paper] [Supplement] [Poster] [Spotlight Talk] [Code]


Invertible Neural Networks as a tool for ill-posed inverse problems. Bremen, September 2019.


Bomberman Multi-agent Reinforcement Learning Environment. For Fundamentals of Machine Learning WS 18/19.
[Framework] [2019 tournament results]


Comparison of Learned Inference Approaches for Image Restoration. Master’s Thesis, September 2016.
Graded 1.0
[Thesis] [Slides]

Steganalyse einer Erweiterung des steganographischen Algorithmus HUGO. Bachelor’s Thesis, April 2013.
Graded 1.2
[Thesis] (German)


Super-Resolution with Regression Tree Fields. Lab Course, May 2015.

Looped mathsy animations. Just a hobby 🙂
[Gallery] [Instagram] [Partial code]