Lightweight Dual-Antagonistic Underwater Image Enhancement Network: A High-Performance Real-Time Approach Combining Knowledge Distillation

Lightweight Dual-Antagonistic Underwater Image Enhancement Network: A High-Performance Real-Time Approach Combining Knowledge Distillation | 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 Lightweight Dual-Antagonistic Underwater Image Enhancement Network: A High-Performance Real-Time Approach Combining Knowledge Distillation ZhiQi Fu, Yuxiang Shen, Yifan Huang, Fei Yuan This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6451625/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Underwater optical imaging, known for its high resolution and rich color information, is widely used in underwater exploration and monitoring. However, it is affected by light absorption and scattering, leading to color attenuation, blurring, and low contrast, which impact visual tasks. Meanwhile, the development of underwater applications towards mobile platforms poses challenges for the efficient deployment of models due to limited computational resources. To address these challenges, this paper proposes a lightweight underwater image enhancement network, WDGA L (Water DOOC GAN Air Light), which integrates human visual dual-opponent characteristics with knowledge distillation. Inspired by human color constancy, the network is designed with a dual-opponent mechanism to enhance color restoration and detail clarity, thereby improving adaptability. Additionally, a knowledge distillation strategy is incorporated, introducing fog density feature imitation loss and adaptive local self-feature distillation loss. These components enable the student network to significantly reduce parameter size while maintaining enhancement performance and improving computational efficiency. The proposed lightweight model is successfully deployed on the RK3588 platform, achieving 32.8 FPS for real-time underwater image observation. Experimental results demonstrate that, compared to state-of-the-art (SOTA) methods, WDGA L improves UCIQE and UIQM metrics by 23.7%, verifying its practicality and feasibility in resource constrained underwater environments. WDGA L shows promising applications in marine intelligent devices, offering an efficient and lightweight solution for underwater image enhancement. Underwater Image Enhancement Human Visual Dual-Antagonistic Properties Knowledge Distillation Efficient Real-Time Processing Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted 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-6451625","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":452141506,"identity":"506b55c5-19a9-4e69-814e-8fc3edfaee06","order_by":0,"name":"ZhiQi Fu","email":"","orcid":"","institution":"Xiamen University","correspondingAuthor":false,"prefix":"","firstName":"ZhiQi","middleName":"","lastName":"Fu","suffix":""},{"id":452141507,"identity":"ee89a20b-4c47-4e32-9c97-c8de7788828a","order_by":1,"name":"Yuxiang Shen","email":"","orcid":"","institution":"Xiamen University","correspondingAuthor":false,"prefix":"","firstName":"Yuxiang","middleName":"","lastName":"Shen","suffix":""},{"id":452141510,"identity":"063619f3-22b7-4053-9633-287abef32f19","order_by":2,"name":"Yifan Huang","email":"","orcid":"","institution":"Guilin University of Electronic Technology","correspondingAuthor":false,"prefix":"","firstName":"Yifan","middleName":"","lastName":"Huang","suffix":""},{"id":452141514,"identity":"4b1d36e0-dee6-470e-86a6-1cbafb06ec15","order_by":3,"name":"Fei Yuan","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAyklEQVRIiWNgGAWjYLCCCgYJOQiLjVgtZxgkjEnWwpDYQLQWgxvJzx4cqLBI33DtjAHDh7LDDPyzGwhpSTM3OHBGInfm7BwDxhnnDjNI3DlASEuCmfTHNoncfukcA2betsMMBhIJhLSkf5M4+E8inQ2k5S9xWnLMJA42SCTwg7QwEqNF8sybMokDxyQMZ85OKzjYcy6dR+IGAS18x9O3SRyoqZM3uJ288cGPMms5/hkEtCgcQOKA2Dz41QOBfANBJaNgFIyCUTDiAQDeSkOig2bEQQAAAABJRU5ErkJggg==","orcid":"","institution":"Xiamen University","correspondingAuthor":true,"prefix":"","firstName":"Fei","middleName":"","lastName":"Yuan","suffix":""}],"badges":[],"createdAt":"2025-04-15 06:38:25","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6451625/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6451625/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":103381245,"identity":"80c095f3-d2db-4dec-b3e8-b77efec4ac42","added_by":"auto","created_at":"2026-02-25 05:41:09","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2941823,"visible":true,"origin":"","legend":"","description":"","filename":"JRTIP.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6451625/v1_covered_03b23d40-27ab-4044-af8f-792ecee4c198.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Lightweight Dual-Antagonistic Underwater Image Enhancement Network: A High-Performance Real-Time Approach Combining Knowledge Distillation","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Underwater Image Enhancement, Human Visual Dual-Antagonistic Properties, Knowledge Distillation, Efficient Real-Time Processing","lastPublishedDoi":"10.21203/rs.3.rs-6451625/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6451625/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Underwater optical imaging, known for its high resolution and rich color information, is widely used in underwater exploration and monitoring. However, it is affected by light absorption and scattering, leading to color attenuation, blurring, and low contrast, which impact visual tasks. Meanwhile, the development of underwater applications towards mobile platforms poses challenges for the efficient deployment of models due to limited computational resources. To address these challenges, this paper proposes a lightweight underwater image enhancement network, WDGA L (Water DOOC GAN Air Light), which integrates human visual dual-opponent characteristics with knowledge distillation. Inspired by human color constancy, the network is designed with a dual-opponent mechanism to enhance color restoration and detail clarity, thereby improving adaptability. Additionally, a knowledge distillation strategy is incorporated, introducing fog density feature imitation loss and adaptive local self-feature distillation loss. These components enable the student network to significantly reduce parameter size while maintaining enhancement performance and improving computational efficiency. The proposed lightweight model is successfully deployed on the RK3588 platform, achieving 32.8 FPS for real-time underwater image observation. Experimental results demonstrate that, compared to state-of-the-art (SOTA) methods, WDGA L improves UCIQE and UIQM metrics by 23.7%, verifying its practicality and feasibility in resource constrained underwater environments. WDGA L shows promising applications in marine intelligent devices, offering an efficient and lightweight solution for underwater image enhancement.","manuscriptTitle":"Lightweight Dual-Antagonistic Underwater Image Enhancement Network: A High-Performance Real-Time Approach Combining Knowledge Distillation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-05-08 08:26:13","doi":"10.21203/rs.3.rs-6451625/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"37caf0f1-def8-4b68-b8c4-fefc207e605a","owner":[],"postedDate":"May 8th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-02-25T05:40:45+00:00","versionOfRecord":[],"versionCreatedAt":"2025-05-08 08:26:13","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6451625","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6451625","identity":"rs-6451625","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}