no code implementations • 11 Jan 2023 • Matthias J. Ehrhardt, Lindon Roberts
Estimating hyperparameters has been a long-standing problem in machine learning.
no code implementations • 26 Oct 2022 • Margaret Duff, Ivor J. A. Simpson, Matthias J. Ehrhardt, Neill D. F. Campbell
One such approach uses generative models, trained on ground-truth images, as priors for inverse problems, penalizing reconstructions far from images the generator can produce.
no code implementations • 5 Sep 2022 • Dongdong Chen, Mike Davies, Matthias J. Ehrhardt, Carola-Bibiane Schönlieb, Ferdia Sherry, Julián Tachella
From early image processing to modern computational imaging, successful models and algorithms have relied on a fundamental property of natural signals: symmetry.
no code implementations • 22 Jul 2021 • Margaret Duff, Neill D. F. Campbell, Matthias J. Ehrhardt
The success of generative regularisers depends on the quality of the generative model and so we propose a set of desired criteria to assess generative models and guide future research.
1 code implementation • 23 Feb 2021 • Elena Celledoni, Matthias J. Ehrhardt, Christian Etmann, Brynjulf Owren, Carola-Bibiane Schönlieb, Ferdia Sherry
In this work, we demonstrate that group equivariant convolutional operations can naturally be incorporated into learned reconstruction methods for inverse problems that are motivated by the variational regularisation approach.
1 code implementation • 6 Nov 2020 • Matthias J. Ehrhardt, Lindon Roberts
Here, we apply a recent dynamic accuracy derivative-free optimization method to hyperparameter tuning, which allows inexact evaluations of the learning problem while retaining convergence guarantees.
1 code implementation • 22 Jul 2020 • Matthias J. Ehrhardt
Imaging with multiple modalities or multiple channels is becoming increasingly important for our modern society.
1 code implementation • 23 Jun 2020 • Matthias J. Ehrhardt, Lindon Roberts
A drawback of these techniques is that they are dependent on a number of parameters which have to be set by the user.
no code implementations • 5 Jun 2020 • Elena Celledoni, Matthias J. Ehrhardt, Christian Etmann, Robert I McLachlan, Brynjulf Owren, Carola-Bibiane Schönlieb, Ferdia Sherry
Over the past few years, deep learning has risen to the foreground as a topic of massive interest, mainly as a result of successes obtained in solving large-scale image processing tasks.
1 code implementation • 1 Apr 2020 • Leon Bungert, Matthias J. Ehrhardt
Multi-modality (or multi-channel) imaging is becoming increasingly important and more widely available, e. g. hyperspectral imaging in remote sensing, spectral CT in material sciences as well as multi-contrast MRI and PET-MR in medicine.
2 code implementations • 20 Jun 2019 • Ferdia Sherry, Martin Benning, Juan Carlos De los Reyes, Martin J. Graves, Georg Maierhofer, Guy Williams, Carola-Bibiane Schönlieb, Matthias J. Ehrhardt
The discovery of the theory of compressed sensing brought the realisation that many inverse problems can be solved even when measurements are "incomplete".
no code implementations • 11 Apr 2019 • Martin Benning, Elena Celledoni, Matthias J. Ehrhardt, Brynjulf Owren, Carola-Bibiane Schönlieb
We review the first order conditions for optimality, and the conditions ensuring optimality after discretisation.
1 code implementation • 21 Aug 2018 • Matthias J. Ehrhardt, Pawel Markiewicz, Carola-Bibiane Schönlieb
Uncompressed clinical data from modern positron emission tomography (PET) scanners are very large, exceeding 350 million data points (projection bins).
2 code implementations • 4 Oct 2017 • Leon Bungert, David A. Coomes, Matthias J. Ehrhardt, Jennifer Rasch, Rafael Reisenhofer, Carola-Bibiane Schönlieb
In this paper, we propose a method for increasing the spatial resolution of a hyperspectral image by fusing it with an image of higher spatial resolution that was obtained with a different imaging modality.
2 code implementations • 15 Jun 2017 • Antonin Chambolle, Matthias J. Ehrhardt, Peter Richtárik, Carola-Bibiane Schönlieb
We propose a stochastic extension of the primal-dual hybrid gradient algorithm studied by Chambolle and Pock in 2011 to solve saddle point problems that are separable in the dual variable.
no code implementations • 20 Nov 2015 • Matthias J. Ehrhardt, Marta M. Betcke
Many clinical imaging studies acquire MRI data for more than one of these contrasts---such as for instance T1 and T2 weighted images---which makes the overall scanning procedure very time consuming.