In recent years, deep learning has achieved remarkable empirical success for image
reconstruction. This has catalyzed an ongoing quest for the precise characterization of the …

Learning to optimize (L2O) is an emerging approach that leverages machine learning to
develop optimization methods, aiming at reducing the laborious iterations of hand …

This review provides an introduction to—and overview of—the current state of the art in
neural‐network based regularization methods for inverse problems in imaging. It aims to …

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 …

In this work, we consider the linear inverse problem $ y= Ax+\varepsilon $, where $ A\colon
X\to Y $ is a known linear operator between the separable Hilbert spaces $ X $ and $ Y …

Plug-and-Play (PnP) methods are a class of efficient iterative methods that aim to combine
data fidelity terms and deep denoisers using classical optimization algorithms, such as ISTA …

Inverse problems consist of recovering a signal from a collection of noisy measurements.
These problems can often be cast as feasibility problems; however, additional regularization …

We propose a non-stationary iterated network Tikhonov (iNETT) method for the solution of ill-
posed inverse problems. The iNETT employs deep neural networks to build a data-driven …

Proximal operators are ubiquitous in inverse problems, commonly appearing as part of
algorithmic strategies to regularize problems that are otherwise ill-posed. Modern deep …

There has been significant recent interest in the use of deep learning for regularizing
imaging inverse problems. Most work in the area has focused on regularization imposed …