KESPKSR: A Blind Image Super-resolution Network Combined Kernel Estimation and Structural Prior Knowledge

KESPKSR: A Blind Image Super-resolution Network Combined Kernel Estimation and Structural Prior Knowledge | 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 Article KESPKSR: A Blind Image Super-resolution Network Combined Kernel Estimation and Structural Prior Knowledge Jiajun Zhang, Yuanbo Zhou, Jiang Bi, Yuyang Xue, Wei Deng, Wenlin He, and 5 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3309839/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 8 You are reading this latest preprint version Abstract The goal of blind image super-resolution (BISR) is to recover the corresponding high-resolution image from a given low-resolution image with unknown degradation. Prior related research has primarily focused effectively on utilizing the kernel as prior knowledge to recover the high-frequency components of image. However, they overlooked the function of structural prior information within the same image, which resulted in unsatisfactory recovery performance for textures with strong self-similarity. To address this issue, we propose a two stage blind super-resolution network that is based on kernel estimation strategy and is capable of integrating structural texture as prior knowledge. In the first stage, we utilize a dynamic kernel estimator to achieve degradation presentation embedding. Then, we propose a triple path attention groups consists of triple path attention blocks and a global feature fusion block to extract structural prior information to assist the recovery of details within images. The quantitative and qualitative results on standard benchmarks with various degradation settings, including Gaussian8 and DIV2RK, validate that our proposed method outperforms the state-of-the-art methods in terms of fidelity and recovery of clear details. The relevant code is made available on this link as open source. Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 04 Nov, 2023 Reviews received at journal 27 Sep, 2023 Reviewers agreed at journal 10 Sep, 2023 Reviewers invited by journal 07 Sep, 2023 Editor assigned by journal 06 Sep, 2023 Editor invited by journal 06 Sep, 2023 Submission checks completed at journal 06 Sep, 2023 First submitted to journal 30 Aug, 2023 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-3309839","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":231293625,"identity":"431f6782-7624-4beb-b5f8-843f6cc8ae46","order_by":0,"name":"Jiajun Zhang","email":"","orcid":"","institution":"Fuzhou University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Jiajun","middleName":"","lastName":"Zhang","suffix":""},{"id":231293627,"identity":"34f5fca7-b26d-47b8-a457-63067da7c0a7","order_by":1,"name":"Yuanbo Zhou","email":"","orcid":"","institution":"Fuzhou University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Yuanbo","middleName":"","lastName":"Zhou","suffix":""},{"id":231293628,"identity":"3e0ace68-3f4d-458c-8465-207686fb6b03","order_by":2,"name":"Jiang Bi","email":"","orcid":"","institution":"Beijing Radio and TV Station","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Jiang","middleName":"","lastName":"Bi","suffix":""},{"id":231293632,"identity":"020fb7a5-f931-46cd-b468-bae952ea36dd","order_by":3,"name":"Yuyang Xue","email":"","orcid":"","institution":"University of Edinburgh","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Yuyang","middleName":"","lastName":"Xue","suffix":""},{"id":231293633,"identity":"b1b85cbc-72e5-4736-8cd1-5813e2ad3f96","order_by":4,"name":"Wei Deng","email":"","orcid":"","institution":"The Imperial Vision Technology","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Wei","middleName":"","lastName":"Deng","suffix":""},{"id":231293634,"identity":"1daeea12-aafc-4b52-a07e-0cf5d1f9991f","order_by":5,"name":"Wenlin He","email":"","orcid":"","institution":"Beijing Radio and TV Station","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Wenlin","middleName":"","lastName":"He","suffix":""},{"id":231293635,"identity":"cd677f02-0154-42e5-b478-e93eb80b3bcc","order_by":6,"name":"Tao Zhao","email":"","orcid":"","institution":"Beijing Radio and TV Station","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Tao","middleName":"","lastName":"Zhao","suffix":""},{"id":231293636,"identity":"886e82cf-b12f-430e-a03e-49b1f908c16a","order_by":7,"name":"Kai Sun","email":"","orcid":"","institution":"Beijing Radio and TV Station","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Kai","middleName":"","lastName":"Sun","suffix":""},{"id":231293637,"identity":"17053c56-3aab-4260-82e5-0aa840caf548","order_by":8,"name":"Tong Tong","email":"","orcid":"","institution":"Fuzhou University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Tong","middleName":"","lastName":"Tong","suffix":""},{"id":231293639,"identity":"aae50b04-cb54-4922-83c6-905e5514a3b5","order_by":9,"name":"Qing Zhang","email":"","orcid":"","institution":"Jimei University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Qing","middleName":"","lastName":"Zhang","suffix":""},{"id":231293642,"identity":"abf77232-55a0-42e4-b212-58cefe1e193f","order_by":10,"name":"Qinquan Gao","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA7ElEQVRIiWNgGAWjYFACxgYwxc98AEQxk6BFsi2BaC1QYHCMWC3y7sltD9622eUZH2N/JsFQYZ3YwH72AMOPim04tRieedhuOLctudjsGEOaBMOZ9MQGnrwExp4zt3FrmZHYJs3bxpy47X7DMQnGtsOJDRI8BsyMbQS11CdubmNsk2D8R4QWeQmwlsOJG9iY2SQYG4jQYsDzsE1yzrnjiTOOsTFbJBxLN27jyTE4iM8v8u3pzyTelFUn9rexP7zxocZatp/9jOGDHxV4bDmQwMDAA+MB2QxsQHwAp3qQLQ3IWkbBKBgFo2AUYAMA8RxSpOjkypcAAAAASUVORK5CYII=","orcid":"","institution":"Fuzhou University","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Qinquan","middleName":"","lastName":"Gao","suffix":""}],"badges":[],"createdAt":"2023-08-30 10:44:13","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3309839/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3309839/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":42916189,"identity":"2158d192-39ad-420b-98ac-29bdccf151b7","added_by":"auto","created_at":"2023-09-11 06:51:16","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1039103,"visible":true,"origin":"","legend":"","description":"","filename":"main.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3309839/v1_covered_9fc5d246-6c14-4b67-9e44-eabcde48a705.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"KESPKSR: A Blind Image Super-resolution Network Combined Kernel Estimation and Structural Prior Knowledge","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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-3309839/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3309839/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u0026nbsp; The goal of blind image super-resolution (BISR) is to recover the corresponding high-resolution image from a given low-resolution image with unknown degradation. Prior related research has primarily focused effectively on utilizing the kernel as prior knowledge to recover the high-frequency components of image. However, they overlooked the function of structural prior information within the same image, which resulted in unsatisfactory recovery performance for textures with strong self-similarity. To address this issue, we propose a two stage blind super-resolution network that is based on kernel estimation strategy and is capable of integrating structural texture as prior knowledge. In the first stage, we utilize a dynamic kernel estimator to achieve degradation presentation embedding. Then, we propose a triple path attention groups consists of triple path attention blocks and a global feature fusion block to extract structural prior information to assist the recovery of details within images. The quantitative and qualitative results on standard benchmarks with various degradation settings, including Gaussian8 and DIV2RK, validate that our proposed method outperforms the state-of-the-art methods in terms of fidelity and recovery of clear details. The relevant code is made available on this link as open source.\u003c/p\u003e","manuscriptTitle":"KESPKSR: A Blind Image Super-resolution Network Combined Kernel Estimation and Structural Prior Knowledge","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2023-09-11 06:43:06","doi":"10.21203/rs.3.rs-3309839/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2023-11-04T06:58:55+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2023-09-28T02:06:15+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"8bd0124a-42ef-4349-a478-abb409207309","date":"2023-09-10T22:50:20+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2023-09-07T20:49:22+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2023-09-06T12:29:35+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2023-09-06T10:55:30+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2023-09-06T10:53:13+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2023-08-30T10:30:25+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"fadbf5a4-5634-40bd-8db0-691ff4d7aa44","owner":[],"postedDate":"September 11th, 2023","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2024-04-19T05:44:31+00:00","versionOfRecord":[],"versionCreatedAt":"2023-09-11 06:43:06","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-3309839","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3309839","identity":"rs-3309839","version":["v1"]},"buildId":"ehx78VzkSd0WSzXnipQa-","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}