no code implementations • 27 Mar 2024 • Jannis Chemseddine, Paul Hagemann, Christian Wald, Gabriele Steidl
In inverse problems, many conditional generative models approximate the posterior measure by minimizing a distance between the joint measure and its learned approximation.
no code implementations • 20 Oct 2023 • Jannis Chemseddine, Paul Hagemann, Christian Wald
In inverse problems, many conditional generative models approximate the posterior measure by minimizing a distance between the joint measure and its learned approximation.
1 code implementation • 19 May 2023 • Johannes Hertrich, Christian Wald, Fabian Altekrüger, Paul Hagemann
We prove that the MMD of Riesz kernels, which is also known as energy distance, coincides with the MMD of their sliced version.
1 code implementation • 9 Jun 2022 • Andreas Kofler, Christian Wald, Tobias Schaeffter, Markus Haltmeier, Christoph Kolbitsch
Sparsity-based methods have a long history in the field of signal processing and have been successfully applied to various image reconstruction problems.
1 code implementation • 4 Mar 2022 • Andreas Kofler, Christian Wald, Tobias Schaeffter, Markus Haltmeier, Christoph Kolbitsch
Iterative neural networks - which contain the physical model - can overcome these issues.
no code implementations • 19 Dec 2019 • Andreas Kofler, Markus Haltmeier, Tobias Schaeffter, Marc Kachelrieß, Marc Dewey, Christian Wald, Christoph Kolbitsch
In this paper we present a generalized Deep Learning-based approach for solving ill-posed large-scale inverse problems occuring in medical image reconstruction.
1 code implementation • 1 Apr 2019 • Andreas Kofler, Marc Dewey, Tobias Schaeffter, Christian Wald, Christoph Kolbitsch
Even when trained on only one single subject without data-augmentation, our approach yields results which are similar to the ones obtained on a large training dataset.