Search Results for author: Markus Haltmeier

Found 23 papers, 5 papers with code

Variational multichannel multiclass segmentation\endgraf using unsupervised lifting with CNNs

no code implementations4 Feb 2023 Nadja Gruber, Johannes Schwab, Sebastien Court, Elke Gizewski, Markus Haltmeier

We propose an unsupervised image segmentation approach, that combines a variational energy functional and deep convolutional neural networks.

Image Segmentation Semantic Segmentation +1

Unsupervised Joint Image Transfer and Uncertainty Quantification Using Patch Invariant Networks

1 code implementation9 Jul 2022 Christoph Angermann, Markus Haltmeier, Ahsan Raza Siyal

To ensure a structure-preserving mapping from the input to the target domain, existing methods for unpaired image transfer are commonly based on cycle-consistency, causing additional computational resources and instability due to the learning of an inverse mapping.

Data Augmentation

Convolutional Dictionary Learning by End-To-End Training of Iterative Neural Networks

1 code implementation9 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.

Dictionary Learning Image Reconstruction

A Joint Variational Multichannel Multiphase Segmentation Framework

no code implementations9 Feb 2022 Nadja Gruber, Johannes Schwab, Sebastien Court, Elke Gizewski, Markus Haltmeier

In this paper, we propose a variational image segmentation framework for multichannel multiphase image segmentation based on the Chan-Vese active contour model.

Image Segmentation Semantic Segmentation

Unsupervised Single-shot Depth Estimation using Perceptual Reconstruction

1 code implementation28 Jan 2022 Christoph Angermann, Matthias Schwab, Markus Haltmeier, Christian Laubichler, Steinbjörn Jónsson

Real-time estimation of actual object depth is an essential module for various autonomous system tasks such as 3D reconstruction, scene understanding and condition assessment.

3D Reconstruction Depth Estimation +2

Unpaired Single-Image Depth Synthesis with cycle-consistent Wasserstein GANs

no code implementations31 Mar 2021 Christoph Angermann, Adéla Moravová, Markus Haltmeier, Steinbjörn Jónsson, Christian Laubichler

Real-time estimation of actual environment depth is an essential module for various autonomous system tasks such as localization, obstacle detection and pose estimation.

Depth Estimation Pose Estimation

Surface Topography Characterization Using a Simple Optical Device and Artificial Neural Networks

no code implementations15 Mar 2021 Christoph Angermann, Markus Haltmeier, Christian Laubichler, Steinbjörn Jónsson, Matthias Schwab, Adéla Moravová, Constantin Kiesling, Martin Kober, Wolfgang Fimml

A novel machine learning framework is proposed that allows prediction of the bearing load curves from RGB images of the liner surface that can be collected with a handheld microscope.

BIG-bench Machine Learning

An End-To-End-Trainable Iterative Network Architecture for Accelerated Radial Multi-Coil 2D Cine MR Image Reconstruction

1 code implementation1 Feb 2021 Andreas Kofler, Markus Haltmeier, Tobias Schaeffter, Christoph Kolbitsch

The network is based on a computationally light CNN-component and a subsequent conjugate gradient (CG) method which can be jointly trained end-to-end using an efficient training strategy.

Dictionary Learning Image Reconstruction

Deep Structure Learning using Feature Extraction in Trained Projection Space

no code implementations1 Sep 2020 Christoph Angermann, Markus Haltmeier

Over the last decade of machine learning, convolutional neural networks have been the most striking successes for feature extraction of rich sensory and high-dimensional data.

Regularization of Inverse Problems by Neural Networks

no code implementations6 Jun 2020 Markus Haltmeier, Linh V. Nguyen

Inverse problems arise in a variety of imaging applications including computed tomography, non-destructive testing, and remote sensing.

Sparse aNETT for Solving Inverse Problems with Deep Learning

no code implementations20 Apr 2020 Daniel Obmann, Linh Nguyen, Johannes Schwab, Markus Haltmeier

We propose a sparse reconstruction framework (aNETT) for solving inverse problems.

Unsupervised Adaptive Neural Network Regularization for Accelerated Radial Cine MRI

no code implementations10 Feb 2020 Andreas Kofler, Marc Dewey, Tobias Schaeffter, Christoph Kolbitsch, Markus Haltmeier

We compare the proposed reconstruction scheme to two ground truth-free reconstruction methods, namely a well known Total Variation (TV) minimization and an unsupervised adaptive Dictionary Learning (DIC) method.

Dictionary Learning

Deep synthesis regularization of inverse problems

no code implementations1 Feb 2020 Daniel Obmann, Johannes Schwab, Markus Haltmeier

For these deep learning methods, however, a solid theoretical foundation in the form of reconstruction guarantees is missing.

Neural Networks-based Regularization for Large-Scale Medical Image Reconstruction

no code implementations19 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.

Image Reconstruction SSIM

Random 2.5D U-net for Fully 3D Segmentation

no code implementations23 Oct 2019 Christoph Angermann, Markus Haltmeier

Convolutional neural networks are state-of-the-art for various segmentation tasks.

Augmented NETT Regularization of Inverse Problems

no code implementations8 Aug 2019 Daniel Obmann, Linh Nguyen, Johannes Schwab, Markus Haltmeier

We propose aNETT (augmented NETwork Tikhonov) regularization as a novel data-driven reconstruction framework for solving inverse problems.

A Joint Deep Learning Approach for Automated Liver and Tumor Segmentation

no code implementations21 Feb 2019 Nadja Gruber, Stephan Antholzer, Werner Jaschke, Christian Kremser, Markus Haltmeier

Hepatocellular carcinoma (HCC) is the most common type of primary liver cancer in adults, and the most common cause of death of people suffering from cirrhosis.

Tumor Segmentation

Projection-Based 2.5D U-net Architecture for Fast Volumetric Segmentation

no code implementations1 Feb 2019 Christoph Angermann, Markus Haltmeier, Ruth Steiger, Sergiy Pereverzyev Jr, Elke Gizewski

While for 2D images these networks are also computationally efficient, 3D convolutions have huge storage requirements and require long training time.

Image Based Fashion Product Recommendation with Deep Learning

no code implementations6 May 2018 Hessel Tuinhof, Clemens Pirker, Markus Haltmeier

We develop a two-stage deep learning framework that recommends fashion images based on other input images of similar style.

Product Recommendation Recommendation Systems +1

NETT: Solving Inverse Problems with Deep Neural Networks

no code implementations28 Feb 2018 Housen Li, Johannes Schwab, Stephan Antholzer, Markus Haltmeier

Our theoretical results and framework are different from any previous work using neural networks for solving inverse problems.

Deep Learning for Photoacoustic Tomography from Sparse Data

no code implementations15 Apr 2017 Stephan Antholzer, Markus Haltmeier, Johannes Schwab

In our approach image reconstruction is performed with a deep convolutional neural network (CNN), whose weights are adjusted prior to the actual image reconstruction based on a set of training data.

Image Reconstruction

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