Julius Erbach

I am a Ph.D. candidate in the Center for Learning Systems under the supervision of Prof. Konrad Schindler, Prof. Bernt Schiele and Dr. Jan Eric Lenssen. I am interested in the use of Probabilistic Generative Models like Diffusion Models for computational photography and 3D modeling. Particularly, I want to investigate how to efficiently re-use priors which are incorporated in Foundation models for new applications like inverse problems.

Publications

You can also find my articles on my Google Scholar profile.

Solving Inverse Problems with FLAIR

Julius Erbach, Dominik Narnhofer, Andreas Dombos, Bernt Schiele, Jan Eric Lenssen, Konrad Schindler

Published in arXiv:2506.02680 [cs.CV], 2025

EvShutter: Transforming Events for Unconstrained Rolling Shutter Correction

Julius Erbach, Stepan Tulyakov, Patricia Vitoria, Alfredo Bochicchio, Yuanyou Li

Published in CVPR, 2023

Event-based image deblurring with dynamic motion awareness

Patricia Vitoria, Stamatios Georgoulis, Stepan Tulyakov, Alfredo Bochicchio, Julius Erbach, Yuanyou Li

Published in ECCV, 2022

Time lens: Event-based video frame interpolation

Stepan Tulyakov, Daniel Gehrig, Stamatios Georgoulis, Julius Erbach, Mathias Gehrig, Yuanyou Li, Davide Scaramuzza

Published in CVPR, 2021