Search Results for author: Thomas Pock

Found 59 papers, 16 papers with code

Diffusion-based generation of Histopathological Whole Slide Images at a Gigapixel scale

no code implementations14 Nov 2023 Robert Harb, Thomas Pock, Heimo Müller

They allow the creation of synthesized copies of datasets that can be shared without violating privacy regulations.

Image Generation whole slide images

Product of Gaussian Mixture Diffusion Models

1 code implementation19 Oct 2023 Martin Zach, Erich Kobler, Antonin Chambolle, Thomas Pock

In this work we tackle the problem of estimating the density $ f_X $ of a random variable $ X $ by successive smoothing, such that the smoothed random variable $ Y $ fulfills the diffusion partial differential equation $ (\partial_t - \Delta_1)f_Y(\,\cdot\,, t) = 0 $ with initial condition $ f_Y(\,\cdot\,, 0) = f_X $.

Image Denoising Noise Estimation

On the Relationship Between RNN Hidden State Vectors and Semantic Ground Truth

1 code implementation29 Jun 2023 Edi Muškardin, Martin Tappler, Ingo Pill, Bernhard K. Aichernig, Thomas Pock

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 hypothesis.

Clustering

Non-Log-Concave and Nonsmooth Sampling via Langevin Monte Carlo Algorithms

1 code implementation25 May 2023 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 multimodality.

Bayesian Inference Image Deconvolution

Score-Based Generative Models for Medical Image Segmentation using Signed Distance Functions

no code implementations10 Mar 2023 Lea Bogensperger, Dominik Narnhofer, Filip Ilic, Thomas Pock

Medical image segmentation is a crucial task that relies on the ability to accurately identify and isolate regions of interest in medical images.

Denoising Image Segmentation +3

Learning Gradually Non-convex Image Priors Using Score Matching

no code implementations21 Feb 2023 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.

Denoising

Explicit Diffusion of Gaussian Mixture Model Based Image Priors

no code implementations16 Feb 2023 Martin Zach, Thomas Pock, Erich Kobler, Antonin Chambolle

In this work we tackle the problem of estimating the density $f_X$ of a random variable $X$ by successive smoothing, such that the smoothed random variable $Y$ fulfills $(\partial_t - \Delta_1)f_Y(\,\cdot\,, t) = 0$, $f_Y(\,\cdot\,, 0) = f_X$.

Image Denoising Noise Estimation

Posterior-Variance-Based Error Quantification for Inverse Problems in Imaging

no code implementations23 Dec 2022 Dominik Narnhofer, Andreas Habring, Martin Holler, Thomas Pock

The proposed method employs estimates of the posterior variance together with techniques from conformal prediction in order to obtain coverage guarantees for the error bounds, without making any assumption on the underlying data distribution.

Conformal Prediction

Stable Deep MRI Reconstruction using Generative Priors

no code implementations25 Oct 2022 Martin Zach, Florian Knoll, Thomas Pock

We propose a novel deep neural network based regularizer which is trained in a generative setting on reference magnitude images only.

Decision Making MRI Reconstruction +1

Is Appearance Free Action Recognition Possible?

1 code implementation13 Jul 2022 Filip Ilic, Thomas Pock, Richard P. Wildes

Presently, a methodology and corresponding dataset to isolate the effects of dynamic information in video are missing.

Action Recognition Optical Flow Estimation +1

Computed Tomography Reconstruction using Generative Energy-Based Priors

no code implementations23 Mar 2022 Martin Zach, Erich Kobler, Thomas Pock

We apply the regularizer to limited-angle and few-view CT reconstruction problems, where it outperforms traditional reconstruction algorithms by a large margin.

Computed Tomography (CT)

Learning atrial fiber orientations and conductivity tensors from intracardiac maps using physics-informed neural networks

no code implementations22 Feb 2021 Thomas Grandits, Simone Pezzuto, Francisco Sahli Costabal, Paris Perdikaris, Thomas Pock, Gernot Plank, Rolf Krause

In this work, we employ a recently developed approach, called physics informed neural networks, to learn the fiber orientations from electroanatomical maps, taking into account the physics of the electrical wave propagation.

One-sided Frank-Wolfe algorithms for saddle problems

no code implementations29 Jan 2021 Vladimir Kolmogorov, Thomas Pock

In case $h^*$ is the indicator function of a linear constraint and function $f$ is quadratic, we show a $O(1/n^2)$ convergence rate on the dual objective, requiring $O(n \log n)$ calls of $lmo$.

Optimization and Control

Shared Prior Learning of Energy-Based Models for Image Reconstruction

no code implementations12 Nov 2020 Thomas Pinetz, Erich Kobler, Thomas Pock, Alexander Effland

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-based learning, a patch-based Wasserstein loss functional, and shared prior learning.

Image Reconstruction

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

no code implementations23 Oct 2020 Christian Sormann, Patrick Knöbelreiter, Andreas Kuhn, Mattia Rossi, Thomas Pock, Friedrich Fraundorfer

We therefore show how we can calculate a normalization based on the expected 3D error, which we can then use to normalize the label jumps in the CRF.

Total Deep Variation: A Stable Regularizer for Inverse Problems

1 code implementation15 Jun 2020 Erich Kobler, Alexander Effland, Karl Kunisch, Thomas Pock

In this work, we combine the variational formulation of inverse problems with deep learning by introducing the data-driven general-purpose total deep variation regularizer.

Belief Propagation Reloaded: Learning BP-Layers for Labeling Problems

1 code implementation13 Mar 2020 Patrick Knöbelreiter, Christian Sormann, Alexander Shekhovtsov, Friedrich Fraundorfer, Thomas Pock

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

Optical Flow Estimation Semantic Segmentation

Total Deep Variation for Linear Inverse Problems

1 code implementation CVPR 2020 Erich Kobler, Alexander Effland, Karl Kunisch, Thomas Pock

Diverse inverse problems in imaging can be cast as variational problems composed of a task-specific data fidelity term and a regularization term.

Image Reconstruction Image Restoration

Improving Optical Flow on a Pyramid Level

no code implementations ECCV 2020 Markus Hofinger, Samuel Rota Bulò, Lorenzo Porzi, Arno Knapitsch, Thomas Pock, Peter Kontschieder

In this work we review the coarse-to-fine spatial feature pyramid concept, which is used in state-of-the-art optical flow estimation networks to make exploration of the pixel flow search space computationally tractable and efficient.

Blocking Optical Flow Estimation

On the estimation of the Wasserstein distance in generative models

no code implementations2 Oct 2019 Thomas Pinetz, Daniel Soukup, Thomas Pock

Generative Adversarial Networks (GANs) have been used to model the underlying probability distribution of sample based datasets.

Impact of the latent space on the ability of GANs to fit the distribution

no code implementations25 Sep 2019 Thomas Pinetz, Daniel Soukup, Thomas Pock

The goal of generative models is to model the underlying data distribution of a sample based dataset.

Learned Collaborative Stereo Refinement

no code implementations31 Jul 2019 Patrick Knöbelreiter, Thomas Pock

The proposed variational network arises naturally from unrolling the iterates of a proximal gradient method applied to a variational energy defined in a joint disparity, color, and confidence image space.

Rolling Shutter Correction

Self-Supervised Learning for Stereo Reconstruction on Aerial Images

no code implementations29 Jul 2019 Patrick Knöbelreiter, Christoph Vogel, Thomas Pock

Recent developments established deep learning as an inevitable tool to boost the performance of dense matching and stereo estimation.

Self-Supervised Learning

An Optimal Control Approach to Early Stopping Variational Methods for Image Restoration

no code implementations19 Jul 2019 Alexander Effland, Erich Kobler, Karl Kunisch, Thomas Pock

We investigate a well-known phenomenon of variational approaches in image processing, where typically the best image quality is achieved when the gradient flow process is stopped before converging to a stationary point.

Deblurring Image Deblurring +2

Fast Decomposable Submodular Function Minimization using Constrained Total Variation

1 code implementation NeurIPS 2019 K. S. Sesh Kumar, Francis Bach, Thomas Pock

We consider the problem of minimizing the sum of submodular set functions assuming minimization oracles of each summand function.

Convex-Concave Backtracking for Inertial Bregman Proximal Gradient Algorithms in Non-Convex Optimization

2 code implementations6 Apr 2019 Mahesh Chandra Mukkamala, Peter Ochs, Thomas Pock, Shoham Sabach

Backtracking line-search is an old yet powerful strategy for finding a better step sizes to be used in proximal gradient algorithms.

Deep Learning Methods for Parallel Magnetic Resonance Image Reconstruction

no code implementations1 Apr 2019 Florian Knoll, Kerstin Hammernik, Chi Zhang, Steen Moeller, Thomas Pock, Daniel K. Sodickson, Mehmet Akcakaya

Both linear and non-linear methods are covered, followed by a discussion of recent efforts to further improve parallel imaging using machine learning, and specifically using artificial neural networks.

BIG-bench Machine Learning MRI Reconstruction

Learning Energy Based Inpainting for Optical Flow

1 code implementation9 Nov 2018 Christoph Vogel, Patrick Knöbelreiter, Thomas Pock

Modern optical flow methods are often composed of a cascade of many independent steps or formulated as a black box neural network that is hard to interpret and analyze.

feature selection Optical Flow Estimation

Variational 3D-PIV with Sparse Descriptors

no code implementations9 Apr 2018 Katrin Lasinger, Christoph Vogel, Thomas Pock, Konrad Schindler

We propose a new method for iterative particle reconstruction (IPR), in which the locations and intensities of all particles are inferred in one joint energy minimization.

3D Fluid Flow Estimation with Integrated Particle Reconstruction

1 code implementation9 Apr 2018 Katrin Lasinger, Christoph Vogel, Thomas Pock, Konrad Schindler

We show, for the first time, how to jointly reconstruct both the individual tracer particles and a dense 3D fluid motion field from the image data, using an integrated energy minimization.

3D Reconstruction Motion Estimation

Robust Deformation Estimation in Wood-Composite Materials using Variational Optical Flow

no code implementations13 Feb 2018 Markus Hofinger, Thomas Pock, Thomas Moosbrugger

Wood-composite materials are widely used today as they homogenize humidity related directional deformations.

Optical Flow Estimation

Semantic 3D Reconstruction with Finite Element Bases

no code implementations4 Oct 2017 Audrey Richard, Christoph Vogel, Maros Blaha, Thomas Pock, Konrad Schindler

We propose a novel framework for the discretisation of multi-label problems on arbitrary, continuous domains.

3D Reconstruction valid

Neural EPI-Volume Networks for Shape From Light Field

no code implementations ICCV 2017 Stefan Heber, Wei Yu, Thomas Pock

In the first part the network encodes relevant information from the given input into a set of high-level feature maps.

Scalable Full Flow with Learned Binary Descriptors

no code implementations20 Jul 2017 Gottfried Munda, Alexander Shekhovtsov, Patrick Knöbelreiter, Thomas Pock

We tackle the computation- and memory-intensive operations on the 4D cost volume by a min-projection which reduces memory complexity from quadratic to linear and binary descriptors for efficient matching.

Optical Flow Estimation

Learning a Variational Network for Reconstruction of Accelerated MRI Data

2 code implementations3 Apr 2017 Kerstin Hammernik, Teresa Klatzer, Erich Kobler, Michael P. Recht, Daniel K. Sodickson, Thomas Pock, Florian Knoll

Due to its high computational performance, i. e., reconstruction time of 193 ms on a single graphics card, and the omission of parameter tuning once the network is trained, this new approach to image reconstruction can easily be integrated into clinical workflow.

Image Reconstruction Learning Theory

Real-Time Panoramic Tracking for Event Cameras

1 code implementation15 Mar 2017 Christian Reinbacher, Gottfried Munda, Thomas Pock

In this work we propose a novel method to perform camera tracking of event cameras in a panoramic setting with three degrees of freedom.

Position Visual Odometry

Inertial Proximal Alternating Linearized Minimization (iPALM) for Nonconvex and Nonsmooth Problems

2 code implementations8 Feb 2017 Thomas Pock, Shoham Sabach

In this paper we study nonconvex and nonsmooth optimization problems with semi-algebraic data, where the variables vector is split into several blocks of variables.

Optimization and Control

Real-Time Intensity-Image Reconstruction for Event Cameras Using Manifold Regularisation

1 code implementation21 Jul 2016 Christian Reinbacher, Gottfried Graber, Thomas Pock

In our experiments we verify that solving the variational model on the manifold produces high-quality images without explicitly estimating optical flow.

Image Reconstruction Optical Flow Estimation

Convolutional Networks for Shape From Light Field

no code implementations CVPR 2016 Stefan Heber, Thomas Pock

In this paper we utilize CNNs to predict depth information for given Light Field (LF) data.

Solving Dense Image Matching in Real-Time using Discrete-Continuous Optimization

no code implementations23 Jan 2016 Alexander Shekhovtsov, Christian Reinbacher, Gottfried Graber, Thomas Pock

Dense image matching is a fundamental low-level problem in Computer Vision, which has received tremendous attention from both discrete and continuous optimization communities.

Optical Flow Estimation Stereo Matching +1

Acceleration of the PDHGM on strongly convex subspaces

no code implementations20 Nov 2015 Tuomo Valkonen, Thomas Pock

We propose several variants of the primal-dual method due to Chambolle and Pock.

Deblurring Denoising

Efficient Minimal-Surface Regularization of Perspective Depth Maps in Variational Stereo

no code implementations CVPR 2015 Gottfried Graber, Jonathan Balzer, Stefano Soatto, Thomas Pock

We propose a method for dense three-dimensional surface reconstruction that leverages the strengths of shape-based approaches, by imposing regularization that respects the geometry of the surface, and the strength of depth-map-based stereo, by avoiding costly computation of surface topology.

Surface Reconstruction

Total variation on a tree

no code implementations26 Feb 2015 Vladimir Kolmogorov, Thomas Pock, Michal Rolinek

We consider the problem of minimizing the continuous valued total variation subject to different unary terms on trees and propose fast direct algorithms based on dynamic programming to solve these problems.

A higher-order MRF based variational model for multiplicative noise reduction

no code implementations21 Apr 2014 Yunjin Chen, Wensen Feng, René Ranftl, Hong Qiao, Thomas Pock

The Fields of Experts (FoE) image prior model, a filter-based higher-order Markov Random Fields (MRF) model, has been shown to be effective for many image restoration problems.

Image Restoration

iPiano: Inertial Proximal Algorithm for Non-Convex Optimization

no code implementations18 Apr 2014 Peter Ochs, Yunjin Chen, Thomas Brox, Thomas Pock

A rigorous analysis of the algorithm for the proposed class of problems yields global convergence of the function values and the arguments.

Image Compression Image Denoising

An inertial forward-backward algorithm for monotone inclusions

no code implementations14 Mar 2014 Dirk A. Lorenz, Thomas Pock

In this paper, we propose an inertial forward backward splitting algorithm to compute a zero of the sum of two monotone operators, with one of the two operators being co-coercive.

Revisiting loss-specific training of filter-based MRFs for image restoration

no code implementations16 Jan 2014 Yunjin Chen, Thomas Pock, René Ranftl, Horst Bischof

It is now well known that Markov random fields (MRFs) are particularly effective for modeling image priors in low-level vision.

Image Denoising Image Restoration

Learning $\ell_1$-based analysis and synthesis sparsity priors using bi-level optimization

no code implementations16 Jan 2014 Yunjin Chen, Thomas Pock, Horst Bischof

We then introduce an approach to learn both analysis operator and synthesis dictionary simultaneously by using a unified framework of bi-level optimization.

Dictionary Learning Image Denoising

A bi-level view of inpainting - based image compression

no code implementations16 Jan 2014 Yunjin Chen, René Ranftl, Thomas Pock

Inpainting based image compression approaches, especially linear and non-linear diffusion models, are an active research topic for lossy image compression.

Descriptive Image Compression

Insights into analysis operator learning: From patch-based sparse models to higher-order MRFs

no code implementations13 Jan 2014 Yunjin Chen, René Ranftl, Thomas Pock

Numerical experiments show that our trained models clearly outperform existing analysis operator learning approaches and are on par with state-of-the-art image denoising algorithms.

Image Denoising Image Restoration +1

An Iterated L1 Algorithm for Non-smooth Non-convex Optimization in Computer Vision

no code implementations CVPR 2013 Peter Ochs, Alexey Dosovitskiy, Thomas Brox, Thomas Pock

Here we extend the problem class to linearly constrained optimization of a Lipschitz continuous function, which is the sum of a convex function and a function being concave and increasing on the non-negative orthant (possibly non-convex and nonconcave on the whole space).

Image Denoising Optical Flow Estimation

Filament and Flare Detection in Hα image sequences

no code implementations26 Apr 2013 Gernot Riegler, Thomas Pock, Werner Pötzi, Astrid Veronig

The information produced by our method can be used for near real-time alerts and the statistical analysis of existing data by solar physicists.

A Convex Approach for Image Hallucination

no code implementations26 Apr 2013 Peter Innerhofer, Thomas Pock

In this paper we propose a global convex approach for image hallucination.

Hallucination Image Super-Resolution

Cannot find the paper you are looking for? You can Submit a new open access paper.