4 papers
Imaging with Equivariant Deep Learning
Dongdong Chen, Mike Davies, Matthias J. Ehrhardt +3
From early image processing to modern computational imaging, successful models and algorithms have relied on a fundamental property of natural signals: symmetry. Here symmetry refe…
Equivariant neural networks for inverse problems
Elena Celledoni, Matthias J. Ehrhardt, Christian Etmann +3
In recent years the use of convolutional layers to encode an inductive bias (translational equivariance) in neural networks has proven to be a very fruitful idea. The successes of…
Structure preserving deep learning
Elena Celledoni, Matthias J. Ehrhardt, Christian Etmann +4
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…
Learning the Sampling Pattern for MRI
Ferdia Sherry, Martin Benning, Juan Carlos De los Reyes +5
The discovery of the theory of compressed sensing brought the realisation that many inverse problems can be solved even when measurements are "incomplete". This is particularly int…