Uncertain Semantics Meet Implicit Constraints: A New Frontier in Real-World UHD Image Deblurring

Uncertain Semantics Meet Implicit Constraints: A New Frontier in Real-World UHD 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 Uncertain Semantics Meet Implicit Constraints: A New Frontier in Real-World UHD Image Deblurring Meng Zhao, Shuning Sun, Zhuoran Zheng This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6840511/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 5 You are reading this latest preprint version Abstract Image deblurring has always been a challenging problem in computer vision, especially when dealing with real-world images. Despite the significant progress made by current methods, they often struggle to handle Ultra-High-Definition (UHD) images due to computational resource limitations. In this paper, we propose a novel UHD image restoration model called SeMIR, which focuses on the UHD deblurring task and can run a full-resolution UHD image with a single GPU shader. The design of our approach is based on two well-established insights. First, existing image enhancement methods with the help of foundation models over-trust the decisions of foundation models, here we model uncertainty by modeling the decisions of foundation models to boost the performance of image deblurring. Second, explicit deep network inference tends to exhibit overfitting. Here, we design an Implicit Feature Processor (IFP) module, which constrains the model’s inference to accurately output clear images through global and local modeling. Meanwhile, we also contribute a new UHD image dataset, UHD2B, which comprises 2, 025 pairs of UHD images. The dataset includes a diverse range of scenes and environmental conditions and provides a standardized benchmark for evaluating and comparing different methods. By evaluating both quantitatively and qualitatively on two standard benchmarks, SeMIR’s efficient performance is remarkable, with an inference time of only 2 ms for each 4K image. Image deblurring UHD image restoration UHD image dataset Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 11 Jun, 2025 Reviewers invited by journal 11 Jun, 2025 Editor assigned by journal 09 Jun, 2025 Submission checks completed at journal 09 Jun, 2025 First submitted to journal 07 Jun, 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-6840511","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":470020490,"identity":"fb443125-b405-4bf5-bfee-0ce63316940d","order_by":0,"name":"Meng Zhao","email":"","orcid":"","institution":"Zaozhuang University","correspondingAuthor":false,"prefix":"","firstName":"Meng","middleName":"","lastName":"Zhao","suffix":""},{"id":470020491,"identity":"63fcf808-a5df-4992-bfa0-b572da9d3552","order_by":1,"name":"Shuning Sun","email":"","orcid":"","institution":"University of Chinese Academy of Sciences","correspondingAuthor":false,"prefix":"","firstName":"Shuning","middleName":"","lastName":"Sun","suffix":""},{"id":470020493,"identity":"c9821313-14c5-424c-922d-eae124f7bbe8","order_by":2,"name":"Zhuoran Zheng","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA70lEQVRIiWNgGAWjYDACCQglx8BwAMxgbCBWizFYywFStCSCVRKlRX5287GHX/7cS9/OeMb48wcGG9kNB5ifPcCnhXHOsXRjGZ7i3J0NZ8wkDjCkGW84wGZugE8Ls0SOmbSERELuhgNnzIAOO5y44QAPmwQ+LWwS+d+kJQwS0g0OnDH+cIDhP2EtPBI5bJIfEhISgFoMgA47QFiLhESamTTDgQTDDQeOlUmcMUg2nnmYzQyvFvkZyc8kf/xJkDe4cXjzh4oKO9m+483P8GoBAWYesH0HgAQoqJgJqQcCxh8gkr+BCKWjYBSMglEwIgEAMRBMFWKZa+UAAAAASUVORK5CYII=","orcid":"","institution":"Sun Yat-sen University","correspondingAuthor":true,"prefix":"","firstName":"Zhuoran","middleName":"","lastName":"Zheng","suffix":""}],"badges":[],"createdAt":"2025-06-07 04:38:17","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6840511/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6840511/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":84667310,"identity":"c18e9f64-b4d4-4b3b-aad2-b27462e789bf","added_by":"auto","created_at":"2025-06-16 05:55:26","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3271518,"visible":true,"origin":"","legend":"","description":"","filename":"SeM.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6840511/v1_covered_47f7e878-3315-4f3d-9d96-bd14d94dcc02.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Uncertain Semantics Meet Implicit Constraints: A New Frontier in Real-World UHD Image Deblurring","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"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, UHD image restoration, UHD image dataset","lastPublishedDoi":"10.21203/rs.3.rs-6840511/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6840511/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eImage deblurring has always been a challenging problem in computer vision, especially when dealing with real-world images. Despite the significant progress made by current methods, they often struggle to handle Ultra-High-Definition (UHD) images due to computational resource limitations. In this paper, we propose a novel UHD image restoration model called SeMIR, which focuses on the UHD deblurring task and can run a full-resolution UHD image with a single GPU shader. The design of our approach is based on two well-established insights. First, existing image enhancement methods with the help of foundation models over-trust the decisions of foundation models, here we model uncertainty by modeling the decisions of foundation models to boost the performance of image deblurring. Second, explicit deep network inference tends to exhibit overfitting. Here, we design an Implicit Feature Processor (IFP) module, which constrains the model’s inference to accurately output clear images through global and local modeling. Meanwhile, we also contribute a new UHD image dataset, UHD2B, which comprises 2, 025 pairs of UHD images. The dataset includes a diverse range of scenes and environmental conditions and provides a standardized benchmark for evaluating and comparing different methods. By evaluating both quantitatively and qualitatively on two standard benchmarks, SeMIR’s efficient performance is remarkable, with an inference time of only 2 ms for each 4K image.\u003c/p\u003e","manuscriptTitle":"Uncertain Semantics Meet Implicit Constraints: A New Frontier in Real-World UHD Image Deblurring","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-06-16 05:47:18","doi":"10.21203/rs.3.rs-6840511/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-06-11T21:40:25+00:00","index":"","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-06-11T21:39:47+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-06-09T10:56:27+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-06-09T10:53:16+00:00","index":"","fulltext":""},{"type":"submitted","content":"Signal, Image and Video Processing","date":"2025-06-07T04:30:24+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":"68838070-a934-41ec-b81e-15c04ca439dd","owner":[],"postedDate":"June 16th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2025-06-24T00:38:17+00:00","versionOfRecord":[],"versionCreatedAt":"2025-06-16 05:47:18","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6840511","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6840511","identity":"rs-6840511","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}