Deep-learning-based tomographic imaging is an important application of artificial
intelligence and a new frontier of machine learning. Deep learning has been widely used in …

Plug-and-play (PnP) priors constitute one of the most widely used frameworks for solving
computational imaging problems through the integration of physical models and learned …

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

Recent efforts on solving inverse problems in imaging via deep neural networks use
architectures inspired by a fixed number of iterations of an optimization method. The number …

While deep neural networks (DNN) based single image super-resolution (SISR) methods
are rapidly gaining popularity, they are mainly designed for the widely-used bicubic …

In this work we introduce a novel stochastic algorithm dubbed SNIPS, which draws samples
from the posterior distribution of any linear inverse problem, where the observation is …

Abstract Plug-and-play (PnP) is a non-convex framework that integrates modern denoising
priors, such as BM3D or deep learning-based denoisers, into ADMM or other proximal …

Abstract Plug-and-Play (PnP) methods solve ill-posed inverse problems through iterative
proximal algorithms by replacing a proximal operator by a denoising operation. When …

Plug-and-Play methods constitute a class of iterative algorithms for imaging problems where
regularization is performed by an off-the-shelf denoiser. Although Plug-and-Play methods …

Image denoising—removal of additive white Gaussian noise from an image—is one of the
oldest and most studied problems in image processing. Extensive work over several …