Hierarchical Adaptive Attention and Multi-Scale Transformer for Ghost- Free HDR Imaging

Hierarchical Adaptive Attention and Multi-Scale Transformer for Ghost- Free HDR Imaging | 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 Hierarchical Adaptive Attention and Multi-Scale Transformer for Ghost- Free HDR Imaging ZEBIN WEN, Shu Gong, Caihua Qiu, Wei Gao This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6962959/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 High Dynamic Range (HDR) imaging synthesizes vivid images by merging multiple low dynamic range (LDR) images of different exposures. Nevertheless, in dynamic scenes, object motion or camera commonly introduce ghosting artifacts, severely degrading image quality. Although numerous DNN-based methods have been proposed to address this issue, existing solutions remain unsatisfactory. Spatial attention-based approaches often struggle to cope with complex scenarios characterized by random luminance fluctuations and large-scale motion, while conventional HDR deghosting models that rely on CNN during the fusion stage are hampered by limited receptive fields, lack of dynamic weighting and the absence of multi-scale capabilities.To overcome these limitations, we propose two innovative modules. The Luminance Adaptive Channel Attention (LACA) module dynamically and adaptively modulates channel- wise weights across multiple scales. This enables precise information balancing among channels, effectively suppressing ghosting artifacts and alleviating color saturation issues, thereby yielding refined feature representations that enhance the HDR fusion process.The Multi-Scale Residual Swin Transformer Block (MSRSTB), empowered by a multi-scale Transformer architecture, provides an expansive receptive field and dynamic weighting mechanism. It adeptly handles diverse motion patterns, integrating features in a hierarchical, coarse-to-fine manner, and efficiently manages regions with varying exposure levels. As a result, it significantly reduces saturation artifacts and mitigates ghosting, facilitating high-quality HDR image reconstruction in challenging scenarios. Comprehensive qualitative and quantitative evaluations emonstrate that our proposed modules outperform state-of-the-art methods. High Dynamic Range imaging Ghosting artifacts Saturation Luminance Adaptive Chan- nel Attention Multiple Scales Multi- Scale Residual Swin Transformer Block Coarse-to-Fine Expansive Receptive Field Dynamic Weighting Mechanism Full Text Additional Declarations No competing interests reported. Supplementary Files AIreport.pdf Similarityreport.pdf 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-6962959","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":483279245,"identity":"df67e6ba-7a3e-4b32-8887-1ddfe5cb0b94","order_by":0,"name":"ZEBIN WEN","email":"","orcid":"","institution":"Guangdong University Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"ZEBIN","middleName":"","lastName":"WEN","suffix":""},{"id":483279246,"identity":"0ee93252-4929-4cec-bd9e-667f4586febe","order_by":1,"name":"Shu Gong","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA10lEQVRIiWNgGAWjYLACxgYgwcN84MCHCtK0sCUenHGGNC08xod5W4hQLe/ee/jlzx2HGeR9znw4wNvAIM8vdgC/FsMz59Ksec8cZjA827vhgOQOBsOZsxMIaJmRY2bM2AbU0s+74YDhGYYEg9tEaDH8CdbC8+BAYhsRWuQlcowf8AK1yPP2MBw4SIwWA54zZsy8belAxjGDgw1nJAj7Rb69x/jjzzZrBvme5Mef/1TYyPNLE7LlAAObBJCu33AAzJfArxxsSwMD8wcoYxSMglEwCkYBdgAAju1KPx1aYSYAAAAASUVORK5CYII=","orcid":"","institution":"Guangdong University Science and Technology","correspondingAuthor":true,"prefix":"","firstName":"Shu","middleName":"","lastName":"Gong","suffix":""},{"id":483279247,"identity":"d54c587a-8c41-43d9-89fc-96a15fe89de2","order_by":2,"name":"Caihua Qiu","email":"","orcid":"","institution":"Guangdong University Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Caihua","middleName":"","lastName":"Qiu","suffix":""},{"id":483279248,"identity":"0631d400-cb97-45a4-b429-cd556aa2ec59","order_by":3,"name":"Wei Gao","email":"","orcid":"","institution":"Hohai University","correspondingAuthor":false,"prefix":"","firstName":"Wei","middleName":"","lastName":"Gao","suffix":""}],"badges":[],"createdAt":"2025-06-24 07:53:11","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6962959/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6962959/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":107396615,"identity":"3cc4b67a-8dfe-412e-95a1-b51604495c3d","added_by":"auto","created_at":"2026-04-21 06:42:17","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1234918,"visible":true,"origin":"","legend":"","description":"","filename":"SCI.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6962959/v1_covered_5a6f1e7b-222c-4bc8-bec3-87f28331f481.pdf"},{"id":86763538,"identity":"8672f7ea-9d6b-4ed9-bc44-16421fb0f877","added_by":"auto","created_at":"2025-07-15 10:39:19","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":1323937,"visible":true,"origin":"","legend":"","description":"","filename":"AIreport.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6962959/v1/18f706a2d26dec896b8fdfd7.pdf"},{"id":86763521,"identity":"940538e4-34b9-4891-adfc-12e556bf420f","added_by":"auto","created_at":"2025-07-15 10:39:19","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":1442731,"visible":true,"origin":"","legend":"","description":"","filename":"Similarityreport.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6962959/v1/04dec39fba9d8cbbfe64169e.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Hierarchical Adaptive Attention and Multi-Scale Transformer for Ghost- Free HDR Imaging","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":"High Dynamic Range imaging, Ghosting artifacts, Saturation, Luminance Adaptive Chan- nel Attention, Multiple Scales, Multi- Scale Residual Swin Transformer Block, Coarse-to-Fine, Expansive Receptive Field, Dynamic Weighting Mechanism","lastPublishedDoi":"10.21203/rs.3.rs-6962959/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6962959/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eHigh Dynamic Range (HDR) imaging synthesizes vivid images by merging multiple low dynamic range (LDR) images of different exposures. Nevertheless, in dynamic scenes, object motion or camera commonly introduce ghosting artifacts, severely degrading image quality. Although numerous DNN-based methods have been proposed to address this issue, existing solutions remain unsatisfactory. Spatial attention-based approaches often struggle to cope with complex scenarios characterized by random luminance fluctuations and large-scale motion, while conventional HDR deghosting models that rely on CNN during the fusion stage are hampered by limited receptive fields, lack of dynamic weighting and the absence of multi-scale capabilities.To overcome these limitations, we propose two innovative modules. The Luminance Adaptive Channel Attention (LACA) module dynamically and adaptively modulates channel- wise weights across multiple scales. This enables precise information balancing among channels, effectively suppressing ghosting artifacts and alleviating color saturation issues, thereby yielding refined feature representations that enhance the HDR fusion process.The Multi-Scale Residual Swin Transformer Block (MSRSTB), empowered by a multi-scale Transformer architecture, provides an expansive receptive field and dynamic weighting mechanism. It adeptly handles diverse motion patterns, integrating features in a hierarchical, coarse-to-fine manner, and efficiently manages regions with varying exposure levels. As a result, it significantly reduces saturation artifacts and mitigates ghosting, facilitating high-quality HDR image reconstruction in challenging scenarios. Comprehensive qualitative and quantitative evaluations emonstrate that our proposed modules outperform state-of-the-art methods.\u003c/p\u003e","manuscriptTitle":"Hierarchical Adaptive Attention and Multi-Scale Transformer for Ghost- Free HDR Imaging","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-07-15 10:38:50","doi":"10.21203/rs.3.rs-6962959/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":"77717996-e2e6-47a5-a59c-e48218c87657","owner":[],"postedDate":"July 15th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-04-21T06:41:51+00:00","versionOfRecord":[],"versionCreatedAt":"2025-07-15 10:38:50","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6962959","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6962959","identity":"rs-6962959","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}