Using Deep Neural Networks for Inverse Problems in Imaging: Beyond Analytical Methods

Traditionally, analytical methods have been used to solve imaging problems such as image restoration, inpainting, and superresolution (SR). In recent years, the fields of machine and deep learning have gained a lot of momentum in solving such imaging problems, often surpassing the performance provid...

Full description

Saved in:
Bibliographic Details
Published in:IEEE signal processing magazine 2018-01, Vol.35 (1), p.20-36
Main Authors: Lucas, Alice, Iliadis, Michael, Molina, Rafael, Katsaggelos, Aggelos K.
Format: Magazinearticle
Language:English
Subjects:
Analytical models
Artificial neural networks
Biological neural networks
Engineering
Image reconstruction
Image restoration
Inverse problems
Machine learning
Mathematical analysis
Neural networks
Visual systems
Citations: Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Traditionally, analytical methods have been used to solve imaging problems such as image restoration, inpainting, and superresolution (SR). In recent years, the fields of machine and deep learning have gained a lot of momentum in solving such imaging problems, often surpassing the performance provided by analytical approaches. Unlike analytical methods for which the problem is explicitly defined and domain-knowledge carefully engineered into the solution, deep neural networks (DNNs) do not benefit from such prior knowledge and instead make use of large data sets to learn the unknown solution to the inverse problem. In this article, we review deep-learning techniques for solving such inverse problems in imaging. More specifically, we review the popular neural network architectures used for imaging tasks, offering some insight as to how these deep-learning tools can solve the inverse problem. Furthermore, we address some fundamental questions, such as how deeplearning and analytical methods can be combined to provide better solutions to the inverse problem in addition to providing a discussion on the current limitations and future directions of the use of deep learning for solving inverse problem in imaging.
ISSN:1053-5888
1558-0792
DOI:10.1109/MSP.2017.2760358