1.4k citations · 2.8k across the 56 of their papers we have counts for
67 papers
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…
Product of Gaussian Mixture Diffusion Model for non-linear MRI Inversion
Laurenz Nagler, Martin Zach, Thomas Pock
Diffusion models have recently shown remarkable results in magnetic resonance imaging reconstruction. However, the employed networks typically are black-box estimators of the (smoo…
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…
Product of Gaussian Mixture Diffusion Models
Martin Zach, Erich Kobler, Antonin Chambolle +1
In this work we tackle the problem of estimating the density of a random variable by successive smoothing, such that the smoothed random variable fulfills the d…
Subgradient Langevin Methods for Sampling from Non-smooth Potentials
Andreas Habring, Martin Holler, Thomas Pock
This paper is concerned with sampling from probability distributions on admitting a density of the form , where with $K…
On the Relationship Between RNN Hidden State Vectors and Semantic Ground Truth
Edi Muškardin, Martin Tappler, Ingo Pill +2
We examine the assumption that the hidden-state vectors of recurrent neural networks (RNNs) tend to form clusters of semantically similar vectors, which we dub the clustering hypot…
Non-Log-Concave and Nonsmooth Sampling via Langevin Monte Carlo Algorithms
Tim Tsz-Kit Lau, Han Liu, Thomas Pock
We study the problem of approximate sampling from non-log-concave distributions, e.g., Gaussian mixtures, which is often challenging even in low dimensions due to their multimodali…
Learned Discretization Schemes for the Second-Order Total Generalized Variation
Lea Bogensperger, Antonin Chambolle, Alexander Effland +1
The total generalized variation extends the total variation by incorporating higher-order smoothness. Thus, it can also suffer from similar discretization issues related to isotrop…
Score-Based Generative Models for Medical Image Segmentation using Signed Distance Functions
Lea Bogensperger, Dominik Narnhofer, Filip Ilic +1
Medical image segmentation is a crucial task that relies on the ability to accurately identify and isolate regions of interest in medical images. Thereby, generative approaches all…
Learning Gradually Non-convex Image Priors Using Score Matching
Erich Kobler, Thomas Pock
In this paper, we propose a unified framework of denoising score-based models in the context of graduated non-convex energy minimization. We show that for sufficiently large noise…
Explicit Diffusion of Gaussian Mixture Model Based Image Priors
Martin Zach, Thomas Pock, Erich Kobler +1
In this work we tackle the problem of estimating the density of a random variable by successive smoothing, such that the smoothed random variable fulfills $(\partial_…
Bilevel learning of regularization models and their discretization for image deblurring and super-resolution
Tatiana A. Bubba, Luca Calatroni, Ambra Catozzi +6
Bilevel learning is a powerful optimization technique that has extensively been employed in recent years to bridge the world of model-driven variational approaches with data-driven…
Quantum Transport in Open Spin Chains using Neural-Network Quantum States
Johannes Mellak, Enrico Arrigoni, Thomas Pock +1
In this work we study the treatment of asymmetric open quantum systems with neural networks based on the restricted Boltzmann machine. In particular, we are interested in the non-e…
Posterior-Variance-Based Error Quantification for Inverse Problems in Imaging
Dominik Narnhofer, Andreas Habring, Martin Holler +1
In this work, a method for obtaining pixel-wise error bounds in Bayesian regularization of inverse imaging problems is introduced. The proposed method employs estimates of the post…
Stable Deep MRI Reconstruction using Generative Priors
Martin Zach, Florian Knoll, Thomas Pock
Data-driven approaches recently achieved remarkable success in magnetic resonance imaging (MRI) reconstruction, but integration into clinical routine remains challenging due to a l…
Is Appearance Free Action Recognition Possible?
Filip Ilic, Thomas Pock, Richard P. Wildes
Intuition might suggest that motion and dynamic information are key to video-based action recognition. In contrast, there is evidence that state-of-the-art deep-learning video unde…
Computed Tomography Reconstruction using Generative Energy-Based Priors
Martin Zach, Erich Kobler, Thomas Pock
In the past decades, Computed Tomography (CT) has established itself as one of the most important imaging techniques in medicine. Today, the applicability of CT is only limited by…
Learning atrial fiber orientations and conductivity tensors from intracardiac maps using physics-informed neural networks
Thomas Grandits, Simone Pezzuto, Francisco Sahli Costabal +4
Electroanatomical maps are a key tool in the diagnosis and treatment of atrial fibrillation. Current approaches focus on the activation times recorded. However, more information ca…
GEASI: Geodesic-based Earliest Activation Sites Identification in cardiac models
Thomas Grandits, Alexander Effland, Thomas Pock +3
The identification of the initial ventricular activation sequence is a critical step for the correct personalization of patient-specific cardiac models. In healthy conditions, the…
Bayesian Uncertainty Estimation of Learned Variational MRI Reconstruction
Dominik Narnhofer, Alexander Effland, Erich Kobler +3
Recent deep learning approaches focus on improving quantitative scores of dedicated benchmarks, and therefore only reduce the observation-related (aleatoric) uncertainty. However,…
One-sided Frank-Wolfe algorithms for saddle problems
Vladimir Kolmogorov, Thomas Pock
We study a class of convex-concave saddle-point problems of the form where is a linear operator, is th…
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…
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…
PIEMAP: Personalized Inverse Eikonal Model from cardiac Electro-Anatomical Maps
Thomas Grandits, Simone Pezzuto, Jolijn M. Lubrecht +3
Electroanatomical mapping, a keystone diagnostic tool in cardiac electrophysiology studies, can provide high-density maps of the local electric properties of the tissue. It is ther…