Medium Transmission Map Matters for Learning to Restore Real-World Underwater Images

Medium Transmission Map Matters for Learning to Restore Real-World Underwater Images

Underwater visual perception is essentially important for underwater exploration, archeology, ecosystem and so on. The low illumination, light reflections, scattering, absorption and suspended particles inevitably lead to the critically degraded underwater image quality, which causes great challenge...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kai, Yan, Lanyue, Liang, Ziqiang, Zheng, Guoqing, Wang, Yang, Yang
Format: Artikel
Sprache:eng
Schlagworte:
Computer Science - Computer Vision and Pattern Recognition
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Kai, Yan
Lanyue, Liang
Ziqiang, Zheng
Guoqing, Wang
Yang, Yang
description Underwater visual perception is essentially important for underwater exploration, archeology, ecosystem and so on. The low illumination, light reflections, scattering, absorption and suspended particles inevitably lead to the critically degraded underwater image quality, which causes great challenges on recognizing the objects from the underwater images. The existing underwater enhancement methods that aim to promote the underwater visibility, heavily suffer from the poor image restoration performance and generalization ability. To reduce the difficulty of underwater image enhancement, we introduce the media transmission map as guidance to assist in image enhancement. We formulate the interaction between the underwater visual images and the transmission map to obtain better enhancement results. Even with simple and lightweight network configuration, the proposed method can achieve advanced results of 22.6 dB on the challenging Test-R90 with an impressive 30 times faster than the existing models. Comprehensive experimental results have demonstrated the superiority and potential on underwater perception. Paper's code is offered on: https://github.com/GroupG-yk/MTUR-Net.
doi_str_mv 10.48550/arxiv.2203.09414
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2203_09414</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2203_09414</sourcerecordid><originalsourceid>FETCH-LOGICAL-a674-ff108ba29f646395f34cc245ac4a077345d4a9ce17bac2f4d02bbef7cf90489a3</originalsourceid><addsrcrecordid>eNotj8tKxDAYRrNxIaMP4Mq8QGua_GmapQxeBjoMSMVl-ZvLEGibIam3t7eOLj7O5uPAIeSmYiU0UrI7TF_ho-SciZJpqOCSdHtnw_tEu4RznkLOIc50j6d1y-JSpj4m2jpMc5iPdIn0xeUlJrcSx-ItptHS19m69Inrne4mPLp8RS48jtld_3NDuseHbvtctIen3fa-LbBWUHhfsWZArn0NtdDSCzCGg0QDyJQSIC2gNq5SAxruwTI-DM4r4zWDRqPYkNs_7TmrP6UwYfruf_P6c574Aa56S3U</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Medium Transmission Map Matters for Learning to Restore Real-World Underwater Images</title><source>arXiv.org</source><creator>Kai, Yan ; Lanyue, Liang ; Ziqiang, Zheng ; Guoqing, Wang ; Yang, Yang</creator><creatorcontrib>Kai, Yan ; Lanyue, Liang ; Ziqiang, Zheng ; Guoqing, Wang ; Yang, Yang</creatorcontrib><description>Underwater visual perception is essentially important for underwater exploration, archeology, ecosystem and so on. The low illumination, light reflections, scattering, absorption and suspended particles inevitably lead to the critically degraded underwater image quality, which causes great challenges on recognizing the objects from the underwater images. The existing underwater enhancement methods that aim to promote the underwater visibility, heavily suffer from the poor image restoration performance and generalization ability. To reduce the difficulty of underwater image enhancement, we introduce the media transmission map as guidance to assist in image enhancement. We formulate the interaction between the underwater visual images and the transmission map to obtain better enhancement results. Even with simple and lightweight network configuration, the proposed method can achieve advanced results of 22.6 dB on the challenging Test-R90 with an impressive 30 times faster than the existing models. Comprehensive experimental results have demonstrated the superiority and potential on underwater perception. Paper's code is offered on: https://github.com/GroupG-yk/MTUR-Net.</description><identifier>DOI: 10.48550/arxiv.2203.09414</identifier><language>eng</language><subject>Computer Science - Computer Vision and Pattern Recognition</subject><creationdate>2022-03</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,781,886</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2203.09414$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2203.09414$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Kai, Yan</creatorcontrib><creatorcontrib>Lanyue, Liang</creatorcontrib><creatorcontrib>Ziqiang, Zheng</creatorcontrib><creatorcontrib>Guoqing, Wang</creatorcontrib><creatorcontrib>Yang, Yang</creatorcontrib><title>Medium Transmission Map Matters for Learning to Restore Real-World Underwater Images</title><description>Underwater visual perception is essentially important for underwater exploration, archeology, ecosystem and so on. The low illumination, light reflections, scattering, absorption and suspended particles inevitably lead to the critically degraded underwater image quality, which causes great challenges on recognizing the objects from the underwater images. The existing underwater enhancement methods that aim to promote the underwater visibility, heavily suffer from the poor image restoration performance and generalization ability. To reduce the difficulty of underwater image enhancement, we introduce the media transmission map as guidance to assist in image enhancement. We formulate the interaction between the underwater visual images and the transmission map to obtain better enhancement results. Even with simple and lightweight network configuration, the proposed method can achieve advanced results of 22.6 dB on the challenging Test-R90 with an impressive 30 times faster than the existing models. Comprehensive experimental results have demonstrated the superiority and potential on underwater perception. Paper's code is offered on: https://github.com/GroupG-yk/MTUR-Net.</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj8tKxDAYRrNxIaMP4Mq8QGua_GmapQxeBjoMSMVl-ZvLEGibIam3t7eOLj7O5uPAIeSmYiU0UrI7TF_ho-SciZJpqOCSdHtnw_tEu4RznkLOIc50j6d1y-JSpj4m2jpMc5iPdIn0xeUlJrcSx-ItptHS19m69Inrne4mPLp8RS48jtld_3NDuseHbvtctIen3fa-LbBWUHhfsWZArn0NtdDSCzCGg0QDyJQSIC2gNq5SAxruwTI-DM4r4zWDRqPYkNs_7TmrP6UwYfruf_P6c574Aa56S3U</recordid><startdate>20220317</startdate><enddate>20220317</enddate><creator>Kai, Yan</creator><creator>Lanyue, Liang</creator><creator>Ziqiang, Zheng</creator><creator>Guoqing, Wang</creator><creator>Yang, Yang</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20220317</creationdate><title>Medium Transmission Map Matters for Learning to Restore Real-World Underwater Images</title><author>Kai, Yan ; Lanyue, Liang ; Ziqiang, Zheng ; Guoqing, Wang ; Yang, Yang</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a674-ff108ba29f646395f34cc245ac4a077345d4a9ce17bac2f4d02bbef7cf90489a3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><toplevel>online_resources</toplevel><creatorcontrib>Kai, Yan</creatorcontrib><creatorcontrib>Lanyue, Liang</creatorcontrib><creatorcontrib>Ziqiang, Zheng</creatorcontrib><creatorcontrib>Guoqing, Wang</creatorcontrib><creatorcontrib>Yang, Yang</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Kai, Yan</au><au>Lanyue, Liang</au><au>Ziqiang, Zheng</au><au>Guoqing, Wang</au><au>Yang, Yang</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Medium Transmission Map Matters for Learning to Restore Real-World Underwater Images</atitle><date>2022-03-17</date><risdate>2022</risdate><abstract>Underwater visual perception is essentially important for underwater exploration, archeology, ecosystem and so on. The low illumination, light reflections, scattering, absorption and suspended particles inevitably lead to the critically degraded underwater image quality, which causes great challenges on recognizing the objects from the underwater images. The existing underwater enhancement methods that aim to promote the underwater visibility, heavily suffer from the poor image restoration performance and generalization ability. To reduce the difficulty of underwater image enhancement, we introduce the media transmission map as guidance to assist in image enhancement. We formulate the interaction between the underwater visual images and the transmission map to obtain better enhancement results. Even with simple and lightweight network configuration, the proposed method can achieve advanced results of 22.6 dB on the challenging Test-R90 with an impressive 30 times faster than the existing models. Comprehensive experimental results have demonstrated the superiority and potential on underwater perception. Paper's code is offered on: https://github.com/GroupG-yk/MTUR-Net.</abstract><doi>10.48550/arxiv.2203.09414</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2203.09414
ispartof
issn
language eng
recordid cdi_arxiv_primary_2203_09414
source arXiv.org
subjects Computer Science - Computer Vision and Pattern Recognition
title Medium Transmission Map Matters for Learning to Restore Real-World Underwater Images
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-17T02%3A51%3A22IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Medium%20Transmission%20Map%20Matters%20for%20Learning%20to%20Restore%20Real-World%20Underwater%20Images&rft.au=Kai,%20Yan&rft.date=2022-03-17&rft_id=info:doi/10.48550/arxiv.2203.09414&rft_dat=%3Carxiv_GOX%3E2203_09414%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true