No Cover Image

Journal article 67 views 23 downloads

Generative Recorrupted-to-Recorrupted: An Unsupervised Image Denoising Network for Arbitrary Noise Distribution

Yukun Liu Orcid Logo, Bowen Wan, Daming Shi, Cheng Cheng Orcid Logo

Remote Sensing, Volume: 15, Issue: 2, Start page: 364

Swansea University Author: Cheng Cheng Orcid Logo

  • 65952.VoR.pdf

    PDF | Version of Record

    © 2023 by the authors. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license.

    Download (4.85MB)

Check full text

DOI (Published version): 10.3390/rs15020364

Abstract

With the great breakthrough of supervised learning in the field of denoising, more and more works focus on end-to-end learning to train denoisers. In practice, however, it can be very challenging to obtain labels in support of this approach. The premise of this method is effective is that there is c...

Full description

Published in: Remote Sensing
ISSN: 2072-4292
Published: MDPI AG 2023
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa65952
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2024-05-29T13:51:51Z
last_indexed 2024-05-29T13:51:51Z
id cronfa65952
recordtype SURis
fullrecord <?xml version="1.0" encoding="utf-8"?><rfc1807 xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema"><bib-version>v2</bib-version><id>65952</id><entry>2024-04-03</entry><title>Generative Recorrupted-to-Recorrupted: An Unsupervised Image Denoising Network for Arbitrary Noise Distribution</title><swanseaauthors><author><sid>11ddf61c123b99e59b00fa1479367582</sid><ORCID>0000-0003-0371-9646</ORCID><firstname>Cheng</firstname><surname>Cheng</surname><name>Cheng Cheng</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2024-04-03</date><deptcode>MACS</deptcode><abstract>With the great breakthrough of supervised learning in the field of denoising, more and more works focus on end-to-end learning to train denoisers. In practice, however, it can be very challenging to obtain labels in support of this approach. The premise of this method is effective is that there is certain data support, but in practice, it is particularly difficult to obtain labels in the training data. Several unsupervised denoisers have emerged in recent years; however, to ensure their effectiveness, the noise model must be determined in advance, which limits the practical use of unsupervised denoising.n addition, obtaining inaccurate noise prior to noise estimation algorithms leads to low denoising accuracy. Therefore, we design a more practical denoiser that requires neither clean images as training labels nor noise model assumptions. Our method also needs the support of the noise model; the difference is that the model is generated by a residual image and a random mask during the network training process, and the input and target of the network are generated from a single noisy image and the noise model. At the same time, an unsupervised module and a pseudo supervised module are trained. The extensive experiments demonstrate the effectiveness of our framework and even surpass the accuracy of supervised denoising.</abstract><type>Journal Article</type><journal>Remote Sensing</journal><volume>15</volume><journalNumber>2</journalNumber><paginationStart>364</paginationStart><paginationEnd/><publisher>MDPI AG</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic>2072-4292</issnElectronic><keywords>image denoising network; unsupervised; pseudo supervised</keywords><publishedDay>6</publishedDay><publishedMonth>1</publishedMonth><publishedYear>2023</publishedYear><publishedDate>2023-01-06</publishedDate><doi>10.3390/rs15020364</doi><url/><notes/><college>COLLEGE NANME</college><department>Mathematics and Computer Science School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>MACS</DepartmentCode><institution>Swansea University</institution><apcterm>Another institution paid the OA fee</apcterm><funders>This work is supported by the Ministry of Science and Technology China (MOST) Major Program on New Generation of Artificial Intelligence 2030 No. 2018AAA0102200. It is also supported by the Natural Science Foundation China (NSFC) Major Project No. 61827814 and the Shenzhen Science and Technology Innovation Commission (SZSTI) Project No. JCYJ20190808153619413. The experiments in this work were conducted at the National Engineering Laboratory for Big Data System Computing Technology, China.</funders><projectreference/><lastEdited>2024-05-29T14:54:16.3233023</lastEdited><Created>2024-04-03T17:45:48.7049058</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>Yukun</firstname><surname>Liu</surname><orcid>0000-0003-2994-5393</orcid><order>1</order></author><author><firstname>Bowen</firstname><surname>Wan</surname><order>2</order></author><author><firstname>Daming</firstname><surname>Shi</surname><order>3</order></author><author><firstname>Cheng</firstname><surname>Cheng</surname><orcid>0000-0003-0371-9646</orcid><order>4</order></author></authors><documents><document><filename>65952__30480__dcbb5e4e58a24182b0eccfc32b11ec89.pdf</filename><originalFilename>65952.VoR.pdf</originalFilename><uploaded>2024-05-29T14:52:27.4999465</uploaded><type>Output</type><contentLength>5084326</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>© 2023 by the authors. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling v2 65952 2024-04-03 Generative Recorrupted-to-Recorrupted: An Unsupervised Image Denoising Network for Arbitrary Noise Distribution 11ddf61c123b99e59b00fa1479367582 0000-0003-0371-9646 Cheng Cheng Cheng Cheng true false 2024-04-03 MACS With the great breakthrough of supervised learning in the field of denoising, more and more works focus on end-to-end learning to train denoisers. In practice, however, it can be very challenging to obtain labels in support of this approach. The premise of this method is effective is that there is certain data support, but in practice, it is particularly difficult to obtain labels in the training data. Several unsupervised denoisers have emerged in recent years; however, to ensure their effectiveness, the noise model must be determined in advance, which limits the practical use of unsupervised denoising.n addition, obtaining inaccurate noise prior to noise estimation algorithms leads to low denoising accuracy. Therefore, we design a more practical denoiser that requires neither clean images as training labels nor noise model assumptions. Our method also needs the support of the noise model; the difference is that the model is generated by a residual image and a random mask during the network training process, and the input and target of the network are generated from a single noisy image and the noise model. At the same time, an unsupervised module and a pseudo supervised module are trained. The extensive experiments demonstrate the effectiveness of our framework and even surpass the accuracy of supervised denoising. Journal Article Remote Sensing 15 2 364 MDPI AG 2072-4292 image denoising network; unsupervised; pseudo supervised 6 1 2023 2023-01-06 10.3390/rs15020364 COLLEGE NANME Mathematics and Computer Science School COLLEGE CODE MACS Swansea University Another institution paid the OA fee This work is supported by the Ministry of Science and Technology China (MOST) Major Program on New Generation of Artificial Intelligence 2030 No. 2018AAA0102200. It is also supported by the Natural Science Foundation China (NSFC) Major Project No. 61827814 and the Shenzhen Science and Technology Innovation Commission (SZSTI) Project No. JCYJ20190808153619413. The experiments in this work were conducted at the National Engineering Laboratory for Big Data System Computing Technology, China. 2024-05-29T14:54:16.3233023 2024-04-03T17:45:48.7049058 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Yukun Liu 0000-0003-2994-5393 1 Bowen Wan 2 Daming Shi 3 Cheng Cheng 0000-0003-0371-9646 4 65952__30480__dcbb5e4e58a24182b0eccfc32b11ec89.pdf 65952.VoR.pdf 2024-05-29T14:52:27.4999465 Output 5084326 application/pdf Version of Record true © 2023 by the authors. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license. true eng https://creativecommons.org/licenses/by/4.0/
title Generative Recorrupted-to-Recorrupted: An Unsupervised Image Denoising Network for Arbitrary Noise Distribution
spellingShingle Generative Recorrupted-to-Recorrupted: An Unsupervised Image Denoising Network for Arbitrary Noise Distribution
Cheng Cheng
title_short Generative Recorrupted-to-Recorrupted: An Unsupervised Image Denoising Network for Arbitrary Noise Distribution
title_full Generative Recorrupted-to-Recorrupted: An Unsupervised Image Denoising Network for Arbitrary Noise Distribution
title_fullStr Generative Recorrupted-to-Recorrupted: An Unsupervised Image Denoising Network for Arbitrary Noise Distribution
title_full_unstemmed Generative Recorrupted-to-Recorrupted: An Unsupervised Image Denoising Network for Arbitrary Noise Distribution
title_sort Generative Recorrupted-to-Recorrupted: An Unsupervised Image Denoising Network for Arbitrary Noise Distribution
author_id_str_mv 11ddf61c123b99e59b00fa1479367582
author_id_fullname_str_mv 11ddf61c123b99e59b00fa1479367582_***_Cheng Cheng
author Cheng Cheng
author2 Yukun Liu
Bowen Wan
Daming Shi
Cheng Cheng
format Journal article
container_title Remote Sensing
container_volume 15
container_issue 2
container_start_page 364
publishDate 2023
institution Swansea University
issn 2072-4292
doi_str_mv 10.3390/rs15020364
publisher MDPI AG
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
document_store_str 1
active_str 0
description With the great breakthrough of supervised learning in the field of denoising, more and more works focus on end-to-end learning to train denoisers. In practice, however, it can be very challenging to obtain labels in support of this approach. The premise of this method is effective is that there is certain data support, but in practice, it is particularly difficult to obtain labels in the training data. Several unsupervised denoisers have emerged in recent years; however, to ensure their effectiveness, the noise model must be determined in advance, which limits the practical use of unsupervised denoising.n addition, obtaining inaccurate noise prior to noise estimation algorithms leads to low denoising accuracy. Therefore, we design a more practical denoiser that requires neither clean images as training labels nor noise model assumptions. Our method also needs the support of the noise model; the difference is that the model is generated by a residual image and a random mask during the network training process, and the input and target of the network are generated from a single noisy image and the noise model. At the same time, an unsupervised module and a pseudo supervised module are trained. The extensive experiments demonstrate the effectiveness of our framework and even surpass the accuracy of supervised denoising.
published_date 2023-01-06T14:54:15Z
_version_ 1800395403368071168
score 11.016235

Similar Items