Convolutional sparse representations are a form of sparse representation with a dictionary
that has a structure that is equivalent to convolution with a set of linear filters. While effective …

Deep learning based fusion methods have been achieving promising performance in image
fusion tasks. This is attributed to the network architecture that plays a very important role in …

We propose a general framework for denoising high-dimensional measurements which
requires no prior on the signal, no estimate of the noise, and no clean training data. The only …

In last few years, supervised deep learning has emerged as one powerful tool for image
denoising, which trains a denoising network over an external dataset of noisy/clean image …

Deep convolutional networks have become a popular tool for image generation and
restoration. Generally, their excellent performance is imputed to their ability to learn realistic …

Deep convolutional networks have become a popular tool for image generation and
restoration. Generally, their excellent performance is imputed to their ability to learn realistic …

Deep convolutional neural networks are hindered by training instability and feature
redundancy towards further performance improvement. A promising solution is to impose …

Inverse problems in imaging are extensively studied, with a variety of strategies, tools, and
theory that have been accumulated over the years. Recently, this field has been immensely …

Deep neural networks based on unfolding an iterative algorithm, for example, LISTA
(learned iterative shrinkage thresholding algorithm), have been an empirical success for …

The deep image prior was recently introduced as a prior for natural images. It represents
images as the output of a convolutional network with random inputs. For" inference" …