Search Results for author: Erich Kobler

Found 12 papers, 5 papers with code

Faithful Synthesis of Low-dose Contrast-enhanced Brain MRI Scans using Noise-preserving Conditional GANs

1 code implementation26 Jun 2023 Thomas Pinetz, Erich Kobler, Robert Haase, Katerina Deike-Hofmann, Alexander Radbruch, Alexander Effland

Our numerical experiments show that conditional GANs are suitable for generating images at different GBCA dose levels and can be used to augment datasets for virtual contrast models.

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.


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

Constrained and unconstrained deep image prior optimization models with automatic regularization

1 code implementation Computational Optimization and Applications 2022 Pasquale Cascarano, Giorgia Franchini, Erich Kobler, Federica Porta, Andrea Sebastiani

Numerical results demonstrate the robustness with respect to image content, noise levels and hyperparameters of the proposed models on both denoising and deblurring of simulated as well as real natural and medical images.

Deblurring Denoising

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)

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

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.

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

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

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

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