activity
20132026
most citedInertial Proximal Alternating Linearized Minimization (iPALM) for Nonconvex and Nonsmooth Problems

217 citations · 323 across the 12 of their papers we have counts for

collaborators
Showing cs.CVShow all

19 papers · 1 filter

cs.CV2026

Product-of-Gaussian-Mixture Diffusion Models for Joint Nonlinear MRI Reconstruction

Laurenz Nagler, Martin Zach, Thomas Pock

Recently, diffusion models have attracted considerable attention for magnetic resonance image reconstruction due to their high sample quality. However, most existing methods rely o…

cs.CV2024

Selective, Interpretable, and Motion Consistent Privacy Attribute Obfuscation for Action Recognition

Filip Ilic, He Zhao, Thomas Pock +1

Concerns for the privacy of individuals captured in public imagery have led to privacy-preserving action recognition. Existing approaches often suffer from issues arising through o…

cs.CV2020

Shared Prior Learning of Energy-Based Models for Image Reconstruction

Thomas Pinetz, Erich Kobler, Thomas Pock +1

We propose a novel learning-based framework for image reconstruction particularly designed for training without ground truth data, which has three major building blocks: energy-bas…

cs.CV2020

BP-MVSNet: Belief-Propagation-Layers for Multi-View-Stereo

Christian Sormann, Patrick Knöbelreiter, Andreas Kuhn +3

In this work, we propose BP-MVSNet, a convolutional neural network (CNN)-based Multi-View-Stereo (MVS) method that uses a differentiable Conditional Random Field (CRF) layer for re…

cs.CV202012 cited

Total Deep Variation: A Stable Regularizer for Inverse Problems

Erich Kobler, Alexander Effland, Karl Kunisch +1

Various problems in computer vision and medical imaging can be cast as inverse problems. A frequent method for solving inverse problems is the variational approach, which amounts t…

cs.CV2020

Belief Propagation Reloaded: Learning BP-Layers for Labeling Problems

Patrick Knöbelreiter, Christian Sormann, Alexander Shekhovtsov +2

It has been proposed by many researchers that combining deep neural networks with graphical models can create more efficient and better regularized composite models. The main diffi…