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

Using Deep Neural Networks for Inverse Problems in Imaging: Beyond Analytical Methods. Lucas, A., Iliadis, M., Molina, R., & Katsaggelos, A. K. IEEE Signal Processing Magazine, 35(1):20–36, jan, 2018.

Paper doi abstract bibtex

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.

@article{Alice2018,
abstract = {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.},
author = {Lucas, Alice and Iliadis, Michael and Molina, Rafael and Katsaggelos, Aggelos K.},
doi = {10.1109/MSP.2017.2760358},
issn = {1053-5888},
journal = {IEEE Signal Processing Magazine},
month = {jan},
number = {1},
pages = {20--36},
title = {{Using Deep Neural Networks for Inverse Problems in Imaging: Beyond Analytical Methods}},
url = {http://ieeexplore.ieee.org/document/8253590/},
volume = {35},
year = {2018}
}

Downloads: 0

{"_id":"DiAETMSpaPHugvXrS","bibbaseid":"lucas-iliadis-molina-katsaggelos-usingdeepneuralnetworksforinverseproblemsinimagingbeyondanalyticalmethods-2018","author_short":["Lucas, A.","Iliadis, M.","Molina, R.","Katsaggelos, A. K."],"bibdata":{"bibtype":"article","type":"article","abstract":"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.","author":[{"propositions":[],"lastnames":["Lucas"],"firstnames":["Alice"],"suffixes":[]},{"propositions":[],"lastnames":["Iliadis"],"firstnames":["Michael"],"suffixes":[]},{"propositions":[],"lastnames":["Molina"],"firstnames":["Rafael"],"suffixes":[]},{"propositions":[],"lastnames":["Katsaggelos"],"firstnames":["Aggelos","K."],"suffixes":[]}],"doi":"10.1109/MSP.2017.2760358","issn":"1053-5888","journal":"IEEE Signal Processing Magazine","month":"jan","number":"1","pages":"20–36","title":"Using Deep Neural Networks for Inverse Problems in Imaging: Beyond Analytical Methods","url":"http://ieeexplore.ieee.org/document/8253590/","volume":"35","year":"2018","bibtex":"@article{Alice2018,\nabstract = {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.},\nauthor = {Lucas, Alice and Iliadis, Michael and Molina, Rafael and Katsaggelos, Aggelos K.},\ndoi = {10.1109/MSP.2017.2760358},\nissn = {1053-5888},\njournal = {IEEE Signal Processing Magazine},\nmonth = {jan},\nnumber = {1},\npages = {20--36},\ntitle = {{Using Deep Neural Networks for Inverse Problems in Imaging: Beyond Analytical Methods}},\nurl = {http://ieeexplore.ieee.org/document/8253590/},\nvolume = {35},\nyear = {2018}\n}\n","author_short":["Lucas, A.","Iliadis, M.","Molina, R.","Katsaggelos, A. K."],"key":"Alice2018","id":"Alice2018","bibbaseid":"lucas-iliadis-molina-katsaggelos-usingdeepneuralnetworksforinverseproblemsinimagingbeyondanalyticalmethods-2018","role":"author","urls":{"Paper":"http://ieeexplore.ieee.org/document/8253590/"},"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://sites.northwestern.edu/ivpl/files/2023/06/IVPL_Updated_publications-1.bib","dataSources":["KTWAakbPXLGfYseXn","ePKPjG8C6yvpk4mEK","ya2CyA73rpZseyrZ8","D8k2SxfC5dKNRFgro","7Dwzbxq93HWrJEhT6","qhF8zxmGcJfvtdeAg","fvDEHD49E2ZRwE3fb","H7crv8NWhZup4d4by","DHqokWsryttGh7pJE","vRJd4wNg9HpoZSMHD","sYxQ6pxFgA59JRhxi","w2WahSbYrbcCKBDsC","XasdXLL99y5rygCmq","3gkSihZQRfAD2KBo3","t5XMbyZbtPBo4wBGS","bEpHM2CtrwW2qE8FP","teJzFLHexaz5AQW5z"],"keywords":[],"search_terms":["using","deep","neural","networks","inverse","problems","imaging","beyond","analytical","methods","lucas","iliadis","molina","katsaggelos"],"title":"Using Deep Neural Networks for Inverse Problems in Imaging: Beyond Analytical Methods","year":2018}