Retinex-Inspired Dual Attention Transformer for Low-Iight Enhancement

Retinex-Inspired Dual Attention Transformer for Low-Iight Enhancement | 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 Retinex-Inspired Dual Attention Transformer for Low-Iight Enhancement Yunxue Shao, Yijin Diao, Lingfeng Wang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6754355/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 Low-light image enhancement (LLIE) is a fundamental but challenging task due to non-uniform illumination, severe noise, and structure degradation under poor lighting. This paper proposes GLADFormer , a novel Transformer-based framework that extends the one-stage Retinex theory by introducing perturbation terms to jointly model illumination variation and visual corruptions. The architecture consists of three components: a contrastive illumination estimator that extracts discriminative light-up features; a hierarchical corruption restorer based on window attention; and a Pixel-Aware Gated Modulation (PAGM) module for pixel-level refinement. In particular, the restorer adopts a Light-Guided Attention Block (LGAB) which leverages a window-based attention mechanism—Local Chunked Masked Attention (LCMA)—to effectively model localized spatial context while fusing global exposure cues. This design enhances the ability to recover fine details and suppress noise in complex low-light scenes. Additionally, a contrastive loss encourages robust illumination representation learning. Extensive experiments on five LLIE benchmarks and one downstream detection task demonstrate that GLADFormer achieves state-of-the-art performance with strong generalization and low computational cost.Code is available at https://github.com/JJCcxk/GLADFormer . Retinex Illumination adjustment Visual restoration Transfomer Window attention 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-6754355","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":464780924,"identity":"93034aea-5e37-4f6c-a5e3-2c8e00e72ffb","order_by":0,"name":"Yunxue Shao","email":"","orcid":"","institution":"Nanjing Tech University","correspondingAuthor":false,"prefix":"","firstName":"Yunxue","middleName":"","lastName":"Shao","suffix":""},{"id":464780925,"identity":"4e97d02c-c18a-4620-8aff-869c43b69809","order_by":1,"name":"Yijin Diao","email":"","orcid":"","institution":"Nanjing Tech University","correspondingAuthor":false,"prefix":"","firstName":"Yijin","middleName":"","lastName":"Diao","suffix":""},{"id":464780926,"identity":"d23d7de2-b2ea-4d9c-b5bc-a4b4049becf5","order_by":2,"name":"Lingfeng Wang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAx0lEQVRIiWNgGAWjYBACPuYDIMomAcJlI0ILGxtYcRqQZCZNy2GStPAYfi74dT7P4Pj5Awwfyg4z8M9uIKjFWHpm3+1igzPJDIwzzh1mkLhzgIAW+d4N0rw9txM33GBmYOZtO8xgIJFAyBbezb95e85BtPwlUss2aZ4fByBaGInTwv/NmrchuVjyTLLBwZ5z6TwSNwho4WdjS77N88cuj+/4wYcPfpRZy/HPIKAFDBjbIPQBIOYhQj0I/CFS3SgYBaNgFIxMAABhaz8ZI5Ra1gAAAABJRU5ErkJggg==","orcid":"","institution":"Beijing University of Chemical Technology","correspondingAuthor":true,"prefix":"","firstName":"Lingfeng","middleName":"","lastName":"Wang","suffix":""}],"badges":[],"createdAt":"2025-05-27 01:53:16","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6754355/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6754355/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":84424177,"identity":"609597d3-9343-4361-9a87-c4f81263303a","added_by":"auto","created_at":"2025-06-11 19:01:37","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1741557,"visible":true,"origin":"","legend":"","description":"","filename":"SpringerNatureLaTeX.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6754355/v1_covered_901f23e3-c426-4209-baf7-4d860504732f.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Retinex-Inspired Dual Attention Transformer for Low-Iight Enhancement","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":"Retinex, Illumination adjustment, Visual restoration, Transfomer, Window attention","lastPublishedDoi":"10.21203/rs.3.rs-6754355/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6754355/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eLow-light image enhancement (LLIE) is a fundamental but challenging task due to non-uniform illumination, severe noise, and structure degradation under poor lighting. This paper proposes \u003cb\u003eGLADFormer\u003c/b\u003e, a novel Transformer-based framework that extends the one-stage Retinex theory by introducing perturbation terms to jointly model illumination variation and visual corruptions. The architecture consists of three components: a contrastive illumination estimator that extracts discriminative light-up features; a hierarchical corruption restorer based on window attention; and a Pixel-Aware Gated Modulation (PAGM) module for pixel-level refinement. In particular, the restorer adopts a Light-Guided Attention Block (LGAB) which leverages a window-based attention mechanism\u0026mdash;Local Chunked Masked Attention (LCMA)\u0026mdash;to effectively model localized spatial context while fusing global exposure cues. This design enhances the ability to recover fine details and suppress noise in complex low-light scenes. Additionally, a contrastive loss encourages robust illumination representation learning. Extensive experiments on five LLIE benchmarks and one downstream detection task demonstrate that GLADFormer achieves state-of-the-art performance with strong generalization and low computational cost.Code is available at \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://github.com/JJCcxk/GLADFormer\u003c/span\u003e\u003cspan address=\"https://github.com/JJCcxk/GLADFormer\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/p\u003e","manuscriptTitle":"Retinex-Inspired Dual Attention Transformer for Low-Iight Enhancement","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-06-02 18:31:50","doi":"10.21203/rs.3.rs-6754355/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":"0d9852f4-7322-45d2-8207-4757436cef55","owner":[],"postedDate":"June 2nd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-06-11T18:53:28+00:00","versionOfRecord":[],"versionCreatedAt":"2025-06-02 18:31:50","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6754355","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6754355","identity":"rs-6754355","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}