Infrared and visible image fusion network based on low-light image enhancement and attention mechanism

Infrared and visible image fusion network based on low-light image enhancement and attention mechanism | 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 Infrared and visible image fusion network based on low-light image enhancement and attention mechanism Jinbo Lu, Zhen Pei, Jinling Chen, Kunyu Tan, Qi Ran, Hongyan Wang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4494766/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 03 May, 2025 Read the published version in Signal, Image and Video Processing → Version 1 posted 3 You are reading this latest preprint version Abstract The purpose of infrared and visible image fusion is to combine the information of different spectral imaging to improve the visual effect and information richness of the image. However, the visible images collected by the existing public datasets are often dim, and the fused images cannot fully depict the texture details and structure in the visible images. Moreover, most deep learning-based methods fail to consider the global information of input feature maps during the convolutional layer feature extraction process, which leads to additional information loss. To address these issues, this paper proposes an auto-encoder network that integrates low-light image enhancement with an adaptive global attention mechanism. First, a sharpening-smoothing balance model for low-light image enhancement is designed based on the Retinex model. Enhance the structure, texture, and contrast information of low-light images by adjusting the balance index of the model. Then, an adaptive global attention block is added to the auto-encoder network, which enhances features with important information by adaptively learning the weights of each channel in the input feature map, thereby improving the network's feature expression capabilities. Finally, in the fusion part of the auto-encoder network, a deep spatial attention fusion block is proposed to maintain the texture details in the visible image and highlight the thermal target information in the infrared image. Our experiments are validated on MSRS, LLVIP, and TNO datasets. Both qualitative and quantitative analyses demonstrated that our method achieved superior comprehensive performance compared to the state-of-the-art image fusion algorithms of recent years. image fusion visible image enhancement auto-encoder adaptive global attention deep spatial attention Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 03 May, 2025 Read the published version in Signal, Image and Video Processing → Version 1 posted Submission checks completed at journal 29 May, 2024 Editor assigned by journal 29 May, 2024 First submitted to journal 29 May, 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-4494766","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":311969380,"identity":"737c2223-7723-4b14-b6fd-1ee4be17d669","order_by":0,"name":"Jinbo Lu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAo0lEQVRIiWNgGAWjYBACPiA2SGA4wMBPtBY2mBbJBlK0AMEBBoMDRGuRSGAoeLjjjpzx8eQNDD8qthGnxSDxzDNjszPPChh7ztwmRkv+B4PEtsOJ227kGDAzthGlBWQLUMvmGSRr2SBBtBaeByAtz4wlgH45SJRf+NkT2Ax/tt2R429P3vjgRwURWkAWGUDoBOKjhvkBTAuxOkbBKBgFo2CEAQARfjpZmisIKwAAAABJRU5ErkJggg==","orcid":"","institution":"Southwest Petroleum University","correspondingAuthor":true,"prefix":"","firstName":"Jinbo","middleName":"","lastName":"Lu","suffix":""},{"id":311969381,"identity":"6858f6cd-86c2-47ac-8a81-1597437eb9bb","order_by":1,"name":"Zhen Pei","email":"","orcid":"","institution":"Southwest Petroleum University","correspondingAuthor":false,"prefix":"","firstName":"Zhen","middleName":"","lastName":"Pei","suffix":""},{"id":311969382,"identity":"4c312888-6b9c-471b-962b-6b6b7991cb67","order_by":2,"name":"Jinling Chen","email":"","orcid":"","institution":"Southwest Petroleum University","correspondingAuthor":false,"prefix":"","firstName":"Jinling","middleName":"","lastName":"Chen","suffix":""},{"id":311969384,"identity":"c566aa5e-ceb0-4e1f-9d4f-dc0471db9fc1","order_by":3,"name":"Kunyu Tan","email":"","orcid":"","institution":"Southwest Petroleum University","correspondingAuthor":false,"prefix":"","firstName":"Kunyu","middleName":"","lastName":"Tan","suffix":""},{"id":311969386,"identity":"3f2442da-f073-49c7-8484-33ada26064c6","order_by":4,"name":"Qi Ran","email":"","orcid":"","institution":"Southwest Petroleum University","correspondingAuthor":false,"prefix":"","firstName":"Qi","middleName":"","lastName":"Ran","suffix":""},{"id":311969388,"identity":"8327bb44-e885-448c-a01f-41d686ff41b8","order_by":5,"name":"Hongyan Wang","email":"","orcid":"","institution":"University of Electronic Science and Technology of China","correspondingAuthor":false,"prefix":"","firstName":"Hongyan","middleName":"","lastName":"Wang","suffix":""}],"badges":[],"createdAt":"2024-05-29 06:36:24","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4494766/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4494766/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s11760-025-04131-6","type":"published","date":"2025-05-03T15:57:34+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":81988067,"identity":"cebf4fd4-6575-4cbb-9f1a-f81788a8958a","added_by":"auto","created_at":"2025-05-05 16:07:45","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1925000,"visible":true,"origin":"","legend":"","description":"","filename":"InfraredandVisibleImageFusionNetworkBasedonLowlightImageEnhancementandAttentionMechanism.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4494766/v1_covered_cc1a0ab4-dac3-4a74-9d27-ad9c738e9a16.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Infrared and visible image fusion network based on low-light image enhancement and attention mechanism","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"signal-image-and-video-processing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"sivp","sideBox":"Learn more about [Signal, Image and Video Processing](http://link.springer.com/journal/11760)","snPcode":"11760","submissionUrl":"https://submission.nature.com/new-submission/11760/3","title":"Signal, Image and Video Processing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"image fusion, visible image enhancement, auto-encoder, adaptive global attention, deep spatial attention","lastPublishedDoi":"10.21203/rs.3.rs-4494766/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4494766/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe purpose of infrared and visible image fusion is to combine the information of different spectral imaging to improve the visual effect and information richness of the image. However, the visible images collected by the existing public datasets are often dim, and the fused images cannot fully depict the texture details and structure in the visible images. Moreover, most deep learning-based methods fail to consider the global information of input feature maps during the convolutional layer feature extraction process, which leads to additional information loss. To address these issues, this paper proposes an auto-encoder network that integrates low-light image enhancement with an adaptive global attention mechanism. First, a sharpening-smoothing balance model for low-light image enhancement is designed based on the Retinex model. Enhance the structure, texture, and contrast information of low-light images by adjusting the balance index of the model. Then, an adaptive global attention block is added to the auto-encoder network, which enhances features with important information by adaptively learning the weights of each channel in the input feature map, thereby improving the network's feature expression capabilities. Finally, in the fusion part of the auto-encoder network, a deep spatial attention fusion block is proposed to maintain the texture details in the visible image and highlight the thermal target information in the infrared image. Our experiments are validated on MSRS, LLVIP, and TNO datasets. Both qualitative and quantitative analyses demonstrated that our method achieved superior comprehensive performance compared to the state-of-the-art image fusion algorithms of recent years.\u003c/p\u003e","manuscriptTitle":"Infrared and visible image fusion network based on low-light image enhancement and attention mechanism","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-06-11 04:16:20","doi":"10.21203/rs.3.rs-4494766/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"checksComplete","content":"","date":"2024-05-29T08:05:23+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-05-29T08:05:23+00:00","index":"","fulltext":""},{"type":"submitted","content":"Signal, Image and Video Processing","date":"2024-05-29T06:33:52+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"signal-image-and-video-processing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"sivp","sideBox":"Learn more about [Signal, Image and Video Processing](http://link.springer.com/journal/11760)","snPcode":"11760","submissionUrl":"https://submission.nature.com/new-submission/11760/3","title":"Signal, Image and Video Processing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"1185fd7a-30f8-4158-b709-e238407b90e9","owner":[],"postedDate":"June 11th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-05-05T16:05:35+00:00","versionOfRecord":{"articleIdentity":"rs-4494766","link":"https://doi.org/10.1007/s11760-025-04131-6","journal":{"identity":"signal-image-and-video-processing","isVorOnly":false,"title":"Signal, Image and Video Processing"},"publishedOn":"2025-05-03 15:57:34","publishedOnDateReadable":"May 3rd, 2025"},"versionCreatedAt":"2024-06-11 04:16:20","video":"","vorDoi":"10.1007/s11760-025-04131-6","vorDoiUrl":"https://doi.org/10.1007/s11760-025-04131-6","workflowStages":[]},"version":"v1","identity":"rs-4494766","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4494766","identity":"rs-4494766","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}