The recent trend in regularization methods for inverse problems is to replace handcrafted
sparsifying operators with data-driven approaches. Although using such machine learning …

Convolutional analysis operator learning (CAOL) enables the unsupervised training of
convolutional sparsifying autoencoders, taking advantage of large datasets to obtain high …

The emergence of deep-learning-based methods for solving inverse problems has enabled
a significant increase in reconstruction quality. Unfortunately, these new methods often lack …

The emergence of deep-learning-based methods to solve image-reconstruction problems
has enabled a significant increase in quality. Unfortunately, these new methods often lack …

We propose a regularization scheme for image reconstruction that leverages the power of
deep learning while hinging on classic sparsity-promoting models. Many deep-learning …

There has been tremendous research on the design of image regularizers over the years,
from simple Tikhonov and Laplacian to sophisticated sparsity and CNN-based regularizers …

Recently the field of inverse problems has seen a growing usage of mathematically only
partially understood learned and non-learned priors. Based on first principles, we develop a …

Solving ill-posed inverse problems can be done accurately if a regularizer well adapted to
the nature of the data is available. Such regularizer can be systematically linked with the …

Deep denoisers have shown excellent performance in solving inverse problems in signal
and image processing. In order to guarantee the convergence, the denoiser needs to satisfy …

We propose a sparse reconstruction framework (aNETT) for solving inverse problems.
Opposed to existing sparse reconstruction techniques that are based on linear sparsifying …