Dual-Branch Network with Adaptive Rational Nonlinear Function for Image Deblurring

Dual-Branch Network with Adaptive Rational Nonlinear Function for Image Deblurring | 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 Dual-Branch Network with Adaptive Rational Nonlinear Function for Image Deblurring Wenjing Guo, Jieqing Tan, Linsong Mao, Naimang Hu, Shijie Sun This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6775435/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 21 Oct, 2025 Read the published version in Signal, Image and Video Processing → Version 1 posted 5 You are reading this latest preprint version Abstract In the field of deep learning-based image deblurring, while the single transformer architecture possesses strong global modeling capabilities, it still exhibits certain limitations in local feature extraction. To further improve the effectiveness of blind image deblurring, we present ARFF-Transformer-CNN Network (ATCNet) which integrates the local feature extraction capabilities of CNN into existing transformers, proposing a dual-branch network architecture that combines CNN and transformer. Specifically, the CNN branch effectively extracts local image features such as edges and textures through multi-layer convolutional operations, while the Transformer branch captures global image information like long-range dependencies and global contextual information through self-attention mechanisms. We also propose the adaptive rational activation feed forward(ARFF) module as the feedforward layer in the transformer. This module is a feedforward network component that combines the learnable activation functions of KAN networks with depthwise separable convolutions, aiming to enhance the nonlinear representation capability of features. Experimental results demonstrate that this dual-branch network architecture achieves excellent deblurring performance across multiple datasets, significantly improving image clarity and detail representation. Image Deblurring Deep Learning Dual-Branch Network Adaptive Activation Functions Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 21 Oct, 2025 Read the published version in Signal, Image and Video Processing → Version 1 posted Editorial decision: Revision requested 12 Jun, 2025 Reviewers invited by journal 12 Jun, 2025 Editor assigned by journal 31 May, 2025 Submission checks completed at journal 31 May, 2025 First submitted to journal 29 May, 2025 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-6775435","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":470523704,"identity":"a816beb2-494f-4fa4-bc5b-651cf212392d","order_by":0,"name":"Wenjing Guo","email":"","orcid":"","institution":"Hefei University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Wenjing","middleName":"","lastName":"Guo","suffix":""},{"id":470523705,"identity":"165e0908-d4c7-49e7-b420-1a67c2b1c325","order_by":1,"name":"Jieqing Tan","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA1klEQVRIiWNgGAWjYBACxmYgkQBmMh848KGCBC0SDAxsiQdnnCHBNqAWHuPDvC1EKGVuZz544+GO2jr+2T0fDvA2MMjzix0g5DC2ZIvEM8clJO6c3XBAcgeD4czZCYS08JhJJLYdk2C4kbvhgOEZhgSD2wS18H8Da5G/kfPgQGIbUVp42IBaaiQMbuQwHDhInBY2Y4vEtgOSG2+kGRxsOCNB2C+G/Ycf3vzZVscvdyP58ec/FTby/NKEtDSA4+QwjC+BXzkIyEOU1RFWOQpGwSgYBSMXAACiW0m+aWGTHwAAAABJRU5ErkJggg==","orcid":"","institution":"Hefei University of Technology","correspondingAuthor":true,"prefix":"","firstName":"Jieqing","middleName":"","lastName":"Tan","suffix":""},{"id":470523706,"identity":"120655c4-6728-485a-939c-4958c650b7a4","order_by":2,"name":"Linsong Mao","email":"","orcid":"","institution":"Hefei University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Linsong","middleName":"","lastName":"Mao","suffix":""},{"id":470523707,"identity":"3b6bdea4-c0fe-46fe-aa9b-a60457c235ce","order_by":3,"name":"Naimang Hu","email":"","orcid":"","institution":"Hefei University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Naimang","middleName":"","lastName":"Hu","suffix":""},{"id":470523708,"identity":"2ab2eeaa-4ff2-405c-bcf7-1da7a9ddbd55","order_by":4,"name":"Shijie Sun","email":"","orcid":"","institution":"Hefei University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Shijie","middleName":"","lastName":"Sun","suffix":""}],"badges":[],"createdAt":"2025-05-29 10:08:55","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6775435/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6775435/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s11760-025-04870-6","type":"published","date":"2025-10-21T16:17:18+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":94490767,"identity":"0870dd9c-ffe5-4878-ae30-e87a7e067359","added_by":"auto","created_at":"2025-10-27 17:14:57","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":4215915,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6775435/v1_covered_745e56fc-9c67-456c-9985-9708dc0de66f.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Dual-Branch Network with Adaptive Rational Nonlinear Function for Image Deblurring","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 Deblurring, Deep Learning, Dual-Branch Network, Adaptive Activation Functions","lastPublishedDoi":"10.21203/rs.3.rs-6775435/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6775435/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"In the field of deep learning-based image deblurring, while the single transformer architecture possesses strong global modeling capabilities, it still exhibits certain limitations in local feature extraction. To further improve the effectiveness of blind image deblurring, we present ARFF-Transformer-CNN Network (ATCNet) which integrates the local feature extraction capabilities of CNN into existing transformers, proposing a dual-branch network architecture that combines CNN and transformer. Specifically, the CNN branch effectively extracts local image features such as edges and textures through multi-layer convolutional operations, while the Transformer branch captures global image information like long-range dependencies and global contextual information through self-attention mechanisms. We also propose the adaptive rational activation feed forward(ARFF) module as the feedforward layer in the transformer. This module is a feedforward network component that combines the learnable activation functions of KAN networks with depthwise separable convolutions, aiming to enhance the nonlinear representation capability of features. Experimental results demonstrate that this dual-branch network architecture achieves excellent deblurring performance across multiple datasets, significantly improving image clarity and detail representation.","manuscriptTitle":"Dual-Branch Network with Adaptive Rational Nonlinear Function for Image Deblurring","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-06-16 06:38:08","doi":"10.21203/rs.3.rs-6775435/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-06-12T17:22:22+00:00","index":"","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-06-12T17:21:43+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-05-31T11:51:51+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-05-31T11:51:09+00:00","index":"","fulltext":""},{"type":"submitted","content":"Signal, Image and Video Processing","date":"2025-05-29T10:01:51+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":"9d3f6425-89e1-42f7-89c4-46f31dcac8b5","owner":[],"postedDate":"June 16th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-10-27T16:24:24+00:00","versionOfRecord":{"articleIdentity":"rs-6775435","link":"https://doi.org/10.1007/s11760-025-04870-6","journal":{"identity":"signal-image-and-video-processing","isVorOnly":false,"title":"Signal, Image and Video Processing"},"publishedOn":"2025-10-21 16:17:18","publishedOnDateReadable":"October 21st, 2025"},"versionCreatedAt":"2025-06-16 06:38:08","video":"","vorDoi":"10.1007/s11760-025-04870-6","vorDoiUrl":"https://doi.org/10.1007/s11760-025-04870-6","workflowStages":[]},"version":"v1","identity":"rs-6775435","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6775435","identity":"rs-6775435","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}