An Algorithm Unrolling Approach to Deep Blind Image Deblurring

02/09/2019
by   Yuelong Li, et al.
10

Blind image deblurring remains a topic of enduring interest. Learning based approaches, especially those that employ neural networks have emerged to complement traditional model based methods and in many cases achieve vastly enhanced performance. That said, neural network approaches are generally empirically designed and the underlying structures are difficult to interpret. In recent years, a promising technique called algorithm unrolling has been developed that has helped connect iterative algorithms such as those for sparse coding to neural network architectures. However, such connections have not been made yet for blind image deblurring. In this paper, we propose a neural network architecture based on this idea. We first present an iterative algorithm that may be considered as a generalization of the traditional total-variation regularization method in the gradient domain. We then unroll the algorithm to construct a neural network for image deblurring which we refer to as Deep Unrolling for Blind Deblurring (DUBLID). Key algorithm parameters are learned with the help of training images. Our proposed deep network DUBLID achieves significant practical performance gains while enjoying interpretability at the same time. Extensive experimental results show that DUBLID outperforms many state-of-the-art methods and in addition is computationally faster.

READ FULL TEXT

page 1

page 5

page 6

page 7

page 8

page 10

page 12

research
02/09/2019

An Algorithm Unrolling Approach to Deep Image Deblurring

While neural networks have achieved vastly enhanced performance over tra...
research
05/13/2022

Blind Image Inpainting with Sparse Directional Filter Dictionaries for Lightweight CNNs

Blind inpainting algorithms based on deep learning architectures have sh...
research
02/17/2019

Detecting Colorized Images via Convolutional Neural Networks: Toward High Accuracy and Good Generalization

Image colorization achieves more and more realistic results with the inc...
research
09/21/2022

KXNet: A Model-Driven Deep Neural Network for Blind Super-Resolution

Although current deep learning-based methods have gained promising perfo...
research
01/22/2022

Blind Image Deblurring: a Review

This is a review on blind image deblurring. First, we formulate the blin...
research
05/21/2020

Hyperspectral Unmixing Network Inspired by Unfolding an Optimization Problem

The hyperspectral image (HSI) unmixing task is essentially an inverse pr...
research
06/06/2018

Deep Algorithms: designs for networks

A new design methodology for neural networks that is guided by tradition...

Please sign up or login with your details

Forgot password? Click here to reset