{"paper_id":"39b03ab0-9236-444b-940a-a840b802d153","body_text":"Dual-Branch Underwater Image Enhancement Utilizing Bidirectional Supervision Loss, Contrast Loss, and Style Transfer Loss | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Dual-Branch Underwater Image Enhancement Utilizing Bidirectional Supervision Loss, Contrast Loss, and Style Transfer Loss Zhi Qiao, Xinnan Fan, Xinyu Li, Yuanxue Xin, Pengfei Shi This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4273073/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 8 You are reading this latest preprint version Abstract Due to the complexity of underwater environments, underwater images often exhibit multiple forms of degradation. Despite recent notable advancements in underwater image restoration, the scarcity of paired datasets poses significant challenges for future progress in this field. This paper introduces a dual-branch underwater image enhancement network that includes an image restoration branch and an illumination estimation branch, trained using both paired and unpaired datasets to mitigate the scarcity of paired data. The network is jointly trained through supervised and unsupervised methods: in the supervised phase, it uses paired datasets guided by contrast loss, perceptual loss, and bidirectional supervision loss to learn the mapping from underwater to clear images, in the unsupervised phase, it employs unpaired datasets with bidirectional supervision loss and style transfer loss to learn the style of natural images and enhance network generalizability. Experimental results demonstrate that our proposed method performs comparably or better than other methods across multiple datasets, providing valuable insights and techniques for underwater image restoration. Retinex theory Style transfer Contrastive learning Bidirectional supervision Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 25 Aug, 2024 Reviewers agreed at journal 12 Aug, 2024 Reviews received at journal 12 Aug, 2024 Reviewers agreed at journal 08 Aug, 2024 Reviewers invited by journal 08 Aug, 2024 Submission checks completed at journal 17 Apr, 2024 Editor assigned by journal 17 Apr, 2024 First submitted to journal 16 Apr, 2024 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {\"props\":{\"pageProps\":{\"initialData\":{\"identity\":\"rs-4273073\",\"acceptedTermsAndConditions\":true,\"allowDirectSubmit\":false,\"archivedVersions\":[],\"articleType\":\"Research Article\",\"associatedPublications\":[],\"authors\":[{\"id\":292344326,\"identity\":\"a6a9ccef-d342-4d2e-92a3-47faf052c8e0\",\"order_by\":0,\"name\":\"Zhi Qiao\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Hohai University\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Zhi\",\"middleName\":\"\",\"lastName\":\"Qiao\",\"suffix\":\"\"},{\"id\":292344327,\"identity\":\"4bbb7dc0-9194-47f6-86da-dc77e57f2f25\",\"order_by\":1,\"name\":\"Xinnan Fan\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Hohai University\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Xinnan\",\"middleName\":\"\",\"lastName\":\"Fan\",\"suffix\":\"\"},{\"id\":292344328,\"identity\":\"5436dde6-2cde-4338-afc3-7e51018d6681\",\"order_by\":2,\"name\":\"Xinyu Li\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"China Yangtze Power Co., Ltd\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Xinyu\",\"middleName\":\"\",\"lastName\":\"Li\",\"suffix\":\"\"},{\"id\":292344329,\"identity\":\"2447aef5-aa0c-4131-a44f-e4c666596316\",\"order_by\":3,\"name\":\"Yuanxue Xin\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Hohai University\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Yuanxue\",\"middleName\":\"\",\"lastName\":\"Xin\",\"suffix\":\"\"},{\"id\":292344330,\"identity\":\"216f01e4-57e8-4a97-b455-a6ec20b35af4\",\"order_by\":4,\"name\":\"Pengfei Shi\",\"email\":\"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAuklEQVRIiWNgGAWjYDACCcYGhoqKAwlgNvFazpwhTQsQn20jRYv87Oa2Bwfn3ckzOMB88DYPg10eQS0Gdw62Gxzc9qzY4ABbsjUPQ3IxYS0SiW3SH7cdTtxwgMdMmofhQGIDQYfNSGyTODgHpIX/G3FaGG6AtDSAbWEjTovBjcR2gwPHDifOPMxmbDnHIJkYh6U/e3Cg5nBi3/HmhzfeVNgR4TAGBjYIxQy2lAj1CC2jYBSMglEwCnABANPARPP02HP3AAAAAElFTkSuQmCC\",\"orcid\":\"\",\"institution\":\"Hohai University\",\"correspondingAuthor\":true,\"prefix\":\"\",\"firstName\":\"Pengfei\",\"middleName\":\"\",\"lastName\":\"Shi\",\"suffix\":\"\"}],\"badges\":[],\"createdAt\":\"2024-04-16 04:22:18\",\"currentVersionCode\":1,\"declarations\":\"\",\"doi\":\"10.21203/rs.3.rs-4273073/v1\",\"doiUrl\":\"https://doi.org/10.21203/rs.3.rs-4273073/v1\",\"draftVersion\":[],\"editorialEvents\":[],\"editorialNote\":\"\",\"failedWorkflow\":false,\"files\":[{\"id\":55065768,\"identity\":\"ae41722d-4ee2-4f20-a3f7-dd6721ee1ed5\",\"added_by\":\"auto\",\"created_at\":\"2024-04-22 04:22:19\",\"extension\":\"pdf\",\"order_by\":1,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"manuscript-pdf\",\"size\":26837869,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"NPL.pdf\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-4273073/v1_covered_63d6d75e-ec6d-4b9e-86f0-5c5a2282aa47.pdf\"}],\"financialInterests\":\"No competing interests reported.\",\"formattedTitle\":\"Dual-Branch Underwater Image Enhancement Utilizing Bidirectional Supervision Loss, Contrast Loss, and Style Transfer Loss\",\"fulltext\":[],\"fulltextSource\":\"\",\"fullText\":\"\",\"funders\":[],\"hasAdminPriorityOnWorkflow\":false,\"hasManuscriptDocX\":false,\"hasOptedInToPreprint\":true,\"hasPassedJournalQc\":\"\",\"hasAnyPriority\":false,\"hideJournal\":false,\"highlight\":\"\",\"institution\":\"\",\"isAcceptedByJournal\":false,\"isAuthorSuppliedPdf\":true,\"isDeskRejected\":\"\",\"isHiddenFromSearch\":false,\"isInQc\":false,\"isInWorkflow\":false,\"isPdf\":true,\"isPdfUpToDate\":true,\"isWithdrawnOrRetracted\":false,\"journal\":{\"display\":true,\"email\":\"info@researchsquare.com\",\"identity\":\"neural-processing-letters\",\"isNatureJournal\":false,\"hasQc\":true,\"allowDirectSubmit\":false,\"externalIdentity\":\"nepl\",\"sideBox\":\"Learn more about [Neural Processing Letters](http://link.springer.com/journal/11063)\",\"snPcode\":\"11063\",\"submissionUrl\":\"https://submission.nature.com/new-submission/11063/3\",\"title\":\"Neural Processing Letters\",\"twitterHandle\":\"\",\"acdcEnabled\":true,\"dfaEnabled\":true,\"editorialSystem\":\"em\",\"reportingPortfolio\":\"Springer Hybrid\",\"inReviewEnabled\":true,\"inReviewRevisionsEnabled\":false},\"keywords\":\"Retinex theory, Style transfer, Contrastive learning, Bidirectional supervision\",\"lastPublishedDoi\":\"10.21203/rs.3.rs-4273073/v1\",\"lastPublishedDoiUrl\":\"https://doi.org/10.21203/rs.3.rs-4273073/v1\",\"license\":{\"name\":\"CC BY 4.0\",\"url\":\"https://creativecommons.org/licenses/by/4.0/\"},\"manuscriptAbstract\":\"Due to the complexity of underwater environments, underwater images often exhibit multiple forms of degradation. Despite recent notable advancements in underwater image restoration, the scarcity of paired datasets poses significant challenges for future progress in this field. This paper introduces a dual-branch underwater image enhancement network that includes an image restoration branch and an illumination estimation branch, trained using both paired and unpaired datasets to mitigate the scarcity of paired data. The network is jointly trained through supervised and unsupervised methods: in the supervised phase, it uses paired datasets guided by contrast loss, perceptual loss, and bidirectional supervision loss to learn the mapping from underwater to clear images, in the unsupervised phase, it employs unpaired datasets with bidirectional supervision loss and style transfer loss to learn the style of natural images and enhance network generalizability. Experimental results demonstrate that our proposed method performs comparably or better than other methods across multiple datasets, providing valuable insights and techniques for underwater image restoration.\",\"manuscriptTitle\":\"Dual-Branch Underwater Image Enhancement Utilizing Bidirectional Supervision Loss, Contrast Loss, and Style Transfer Loss\",\"msid\":\"\",\"msnumber\":\"\",\"nonDraftVersions\":[{\"code\":1,\"date\":\"2024-04-22 04:05:58\",\"doi\":\"10.21203/rs.3.rs-4273073/v1\",\"editorialEvents\":[{\"type\":\"communityComments\",\"content\":0},{\"type\":\"editorInvitedReview\",\"content\":\"\",\"date\":\"2024-08-26T02:00:49+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"9795877934215451187687079514533537746\",\"date\":\"2024-08-12T15:29:28+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"editorInvitedReview\",\"content\":\"\",\"date\":\"2024-08-12T14:47:47+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"186295471329951123890925564302174141409\",\"date\":\"2024-08-08T12:31:07+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewersInvited\",\"content\":\"\",\"date\":\"2024-08-08T10:28:55+00:00\",\"index\":\"\",\"fulltext\":\"\"},{\"type\":\"checksComplete\",\"content\":\"\",\"date\":\"2024-04-17T07:54:09+00:00\",\"index\":\"\",\"fulltext\":\"\"},{\"type\":\"editorAssigned\",\"content\":\"\",\"date\":\"2024-04-17T07:54:09+00:00\",\"index\":\"\",\"fulltext\":\"\"},{\"type\":\"submitted\",\"content\":\"Neural Processing Letters\",\"date\":\"2024-04-16T04:21:04+00:00\",\"index\":\"\",\"fulltext\":\"\"}],\"status\":\"published\",\"journal\":{\"display\":true,\"email\":\"info@researchsquare.com\",\"identity\":\"neural-processing-letters\",\"isNatureJournal\":false,\"hasQc\":true,\"allowDirectSubmit\":false,\"externalIdentity\":\"nepl\",\"sideBox\":\"Learn more about [Neural Processing Letters](http://link.springer.com/journal/11063)\",\"snPcode\":\"11063\",\"submissionUrl\":\"https://submission.nature.com/new-submission/11063/3\",\"title\":\"Neural Processing Letters\",\"twitterHandle\":\"\",\"acdcEnabled\":true,\"dfaEnabled\":true,\"editorialSystem\":\"em\",\"reportingPortfolio\":\"Springer Hybrid\",\"inReviewEnabled\":true,\"inReviewRevisionsEnabled\":false}}],\"origin\":\"\",\"ownerIdentity\":\"d9aab685-2ff8-4fc7-888c-9a7458e8ae2b\",\"owner\":[],\"postedDate\":\"April 22nd, 2024\",\"published\":true,\"recentEditorialEvents\":[],\"rejectedJournal\":[],\"revision\":\"\",\"amendment\":\"\",\"status\":\"under-review\",\"subjectAreas\":[],\"tags\":[],\"updatedAt\":\"2024-04-22T04:05:58+00:00\",\"versionOfRecord\":[],\"versionCreatedAt\":\"2024-04-22 04:05:58\",\"video\":\"\",\"vorDoi\":\"\",\"vorDoiUrl\":\"\",\"workflowStages\":[]},\"version\":\"v1\",\"identity\":\"rs-4273073\",\"journalConfig\":\"researchsquare\"},\"__N_SSP\":true},\"page\":\"/article/[identity]/[[...version]]\",\"query\":{\"redirect\":\"/article/rs-4273073\",\"identity\":\"rs-4273073\",\"version\":[\"v1\"]},\"buildId\":\"qtupq5eGEP_6zYnWcrvyt\",\"isFallback\":false,\"isExperimentalCompile\":false,\"dynamicIds\":[84888],\"gssp\":true,\"scriptLoader\":[]}","source_license":"CC-BY-4.0","license_restricted":false}