Unsupervised dehazing of multi-scale residuals based on weighted contrast learning

Unsupervised dehazing of multi-scale residuals based on weighted contrast learning | 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 Unsupervised dehazing of multi-scale residuals based on weighted contrast learning Jianing Wang, Yongsheng zhang, Zuoyang Liu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4812948/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 05 Apr, 2025 Read the published version in Signal, Image and Video Processing → Version 1 posted 7 You are reading this latest preprint version Abstract To solve the problem that existing dehazing algorithms have difficulty in capturing paired hazy and clear images in the real world, while unpaired real-world hazy and clear images are readily obtained. In this study, unpaired real-world hazy and clear images are used to realize unsupervised dehazing. Inspired by the Generative Adversarial Network framework, the generator network combines multi-scale dense blocks and attention mechanism and uses adaptive blending operation to speed up network training while ensuring effective delivery of image details. By incorporating contrast learning, a weighted contrastive loss function is introduced, which encourages the recovered image to be close to positive samples and away from negative samples in the embedding space. Meanwhile, multiple loss functions are combined to enhance the generalization ability of the generative adversarial network in order to train the network more effectively. The proposed algorithm is tested on an outdoor public dataset, and the experimental results show that the algorithm has better performance than existing unsupervised dehazing algorithms. unpaired unsupervised dehazing multi-scale dense blocks weighted contrastive loss Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 05 Apr, 2025 Read the published version in Signal, Image and Video Processing → Version 1 posted Editorial decision: Revision requested 18 Aug, 2024 Reviewers agreed at journal 29 Jul, 2024 Reviewers agreed at journal 27 Jul, 2024 Reviewers invited by journal 27 Jul, 2024 Editor assigned by journal 27 Jul, 2024 Submission checks completed at journal 27 Jul, 2024 First submitted to journal 27 Jul, 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-4812948","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":341833647,"identity":"cfdc173e-1bd6-4ba2-ae84-6b7c09014f80","order_by":0,"name":"Jianing Wang","email":"","orcid":"","institution":"Changchun University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Jianing","middleName":"","lastName":"Wang","suffix":""},{"id":341833648,"identity":"51529459-3e24-4bdc-978f-7441247ed726","order_by":1,"name":"Yongsheng zhang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAuUlEQVRIiWNgGAWjYHACxgdQhgHRWphBSiVI0sImQZoW+Rnpzyp+ttXVMbA3b5NgqLlDWAvjjByzm71thyUYeI6VSTAce0ZYC7NEDtttxrYDEgwSOWYSjA2HCWthk0h/VszYVifBIP+GSC08EglmzIxtzEBbeIjUIsHzxliy59xhyTaetGKLhGNEaJFvT3/44UdZHT8/++GNNz7UEKGFQSABQrOBiAQiNDAw8B8gStkoGAWjYBSMZAAAvRAwX5/aGCQAAAAASUVORK5CYII=","orcid":"","institution":"Changchun University of Science and Technology","correspondingAuthor":true,"prefix":"","firstName":"Yongsheng","middleName":"","lastName":"zhang","suffix":""},{"id":341833649,"identity":"cb95a718-b697-41e1-a7da-0b77fc2cad81","order_by":2,"name":"Zuoyang Liu","email":"","orcid":"","institution":"Changchun University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Zuoyang","middleName":"","lastName":"Liu","suffix":""}],"badges":[],"createdAt":"2024-07-27 12:06:24","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4812948/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4812948/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s11760-025-04043-5","type":"published","date":"2025-04-05T15:57:04+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":80082041,"identity":"ed106bc1-a3b7-4356-a042-313351acfdce","added_by":"auto","created_at":"2025-04-07 16:06:06","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":553006,"visible":true,"origin":"","legend":"","description":"","filename":"Unsuperviseddehazingofmultiscaleresidualsbasedonweightedcontrastlearning.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4812948/v1_covered_6ed651c8-1d1a-4556-b5de-0991c8b1f4cb.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Unsupervised dehazing of multi-scale residuals based on weighted contrast learning","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"unpaired, unsupervised dehazing, multi-scale dense blocks, weighted contrastive loss","lastPublishedDoi":"10.21203/rs.3.rs-4812948/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4812948/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eTo solve the problem that existing dehazing algorithms have difficulty in capturing paired hazy and clear images in the real world, while unpaired real-world hazy and clear images are readily obtained. In this study, unpaired real-world hazy and clear images are used to realize unsupervised dehazing. Inspired by the Generative Adversarial Network framework, the generator network combines multi-scale dense blocks and attention mechanism and uses adaptive blending operation to speed up network training while ensuring effective delivery of image details. By incorporating contrast learning, a weighted contrastive loss function is introduced, which encourages the recovered image to be close to positive samples and away from negative samples in the embedding space. Meanwhile, multiple loss functions are combined to enhance the generalization ability of the generative adversarial network in order to train the network more effectively. The proposed algorithm is tested on an outdoor public dataset, and the experimental results show that the algorithm has better performance than existing unsupervised dehazing algorithms.\u003c/p\u003e","manuscriptTitle":"Unsupervised dehazing of multi-scale residuals based on weighted contrast learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-08-22 06:23:59","doi":"10.21203/rs.3.rs-4812948/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-08-19T01:13:55+00:00","index":"","fulltext":""},{"type":"reviewerAgreed","content":"142271509943869982542824972926371095854","date":"2024-07-29T23:06:46+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"215232462462943929722252112131856839090","date":"2024-07-27T18:49:48+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-07-27T18:30:01+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-07-27T12:32:18+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-07-27T12:32:05+00:00","index":"","fulltext":""},{"type":"submitted","content":"Signal, Image and Video Processing","date":"2024-07-27T12:04:26+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":"22989d13-b959-47b0-9af3-61942a4f21f6","owner":[],"postedDate":"August 22nd, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-04-07T16:01:24+00:00","versionOfRecord":{"articleIdentity":"rs-4812948","link":"https://doi.org/10.1007/s11760-025-04043-5","journal":{"identity":"signal-image-and-video-processing","isVorOnly":false,"title":"Signal, Image and Video Processing"},"publishedOn":"2025-04-05 15:57:04","publishedOnDateReadable":"April 5th, 2025"},"versionCreatedAt":"2024-08-22 06:23:59","video":"","vorDoi":"10.1007/s11760-025-04043-5","vorDoiUrl":"https://doi.org/10.1007/s11760-025-04043-5","workflowStages":[]},"version":"v1","identity":"rs-4812948","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4812948","identity":"rs-4812948","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}