A Cascaded Convolutional Neural Network for Image Deblurring and Denoising

A Cascaded Convolutional Neural Network for Image Deblurring and Denoising | 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 A Cascaded Convolutional Neural Network for Image Deblurring and Denoising Mahendra B M, Savita Sonoli, Tarun Gowda This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-2395895/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Although noise management has received a lot ofattention recently, image deblurring is still difficult. Imageswithout any noisy pixels are the focus of the current deblurringnetworks. To explicitly or implicitly lessen the impact of noisypixels on image deblurring, existing methods primarily relyon repetitive noise detection stages. However, these iterativeoptimization procedures and heuristic operations, which aredifficult and time-consuming, are frequently used in these noisypixels detection steps. In this paper we propose a cascaded modelof two separate networks which will handle the noisy pixelswithout any reduction in image quality. Our model aims todenoise an image first and then deblur it. In addition, it wasfound that deblurring an image first, then denoising it, producedbetter results than training a deblurring network on noisy images.Numerous tests demonstrate that this cascaded network performscompetitively in terms of PSNR and SSIM. outlier denoising deblurring ringing artifacts Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted 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-2395895","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":162183603,"identity":"424e58f7-136b-4696-84a9-44a9e84a7700","order_by":0,"name":"Mahendra B M","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA5klEQVRIiWNgGAWjYFACHhBhU98v//gAkCEhQ6yWNMaZDWkJIC08xGo5zLjhQI4BnIsX6LafPfi4gCGNWbLhzOdXN2oseBjYDx/dgE+L2Zm8ZOMZDDZs/Iy926xzjgEdxpOWdgOvlgM5ZtI8DGk8ks2824xz2IBaJHjM8Gs5/8b8Nw/DYQmDYzzPjHP+EaPlRo4ZM1CLgcEZHubHuW1EaXljLM1jkJYgOYPNjDm3T4KHjaBfzucYfuapsEngl2B+/DnnW50cP/vhY3i1QAA4RhjYJMAkYeUIwPyBFNWjYBSMglEwcgAA38tDD38uY64AAAAASUVORK5CYII=","orcid":"","institution":"Visvesvaraya Technological University","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Mahendra","middleName":"B","lastName":"M","suffix":""},{"id":162183606,"identity":"94dd1d7d-e10e-41c2-be3e-811cf156edfc","order_by":1,"name":"Savita Sonoli","email":"","orcid":"","institution":"Visvesvaraya Technological University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Savita","middleName":"","lastName":"Sonoli","suffix":""},{"id":162183609,"identity":"6ff77ef7-0e64-49bb-814d-35fb3514ae1c","order_by":2,"name":"Tarun Gowda","email":"","orcid":"","institution":"Visvesvaraya Technological University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Tarun","middleName":"","lastName":"Gowda","suffix":""}],"badges":[],"createdAt":"2022-12-20 05:59:14","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-2395895/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-2395895/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":33803776,"identity":"f4cf3d19-20ed-4b91-b264-ffe3ca1166f1","added_by":"auto","created_at":"2023-03-05 18:59:46","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":4863969,"visible":true,"origin":"","legend":"","description":"","filename":"MahendraBM.pdf","url":"https://assets-eu.researchsquare.com/files/rs-2395895/v1_covered.pdf"},{"id":30833971,"identity":"dd376797-3966-4e2b-b96c-7ab2f8b634c2","added_by":"auto","created_at":"2022-12-28 11:36:03","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":4873913,"visible":true,"origin":"","legend":"","description":"","filename":"MahendraBM.pdf","url":"https://assets-eu.researchsquare.com/files/rs-2395895/v1/05f0826db63d3eeef7828e40.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Cascaded Convolutional Neural Network for Image Deblurring and Denoising","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"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":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"outlier, denoising, deblurring, ringing artifacts","lastPublishedDoi":"10.21203/rs.3.rs-2395895/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-2395895/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Although noise management has received a lot ofattention recently, image deblurring is still difficult. Imageswithout any noisy pixels are the focus of the current deblurringnetworks. To explicitly or implicitly lessen the impact of noisypixels on image deblurring, existing methods primarily relyon repetitive noise detection stages. However, these iterativeoptimization procedures and heuristic operations, which aredifficult and time-consuming, are frequently used in these noisypixels detection steps. In this paper we propose a cascaded modelof two separate networks which will handle the noisy pixelswithout any reduction in image quality. Our model aims todenoise an image first and then deblur it. In addition, it wasfound that deblurring an image first, then denoising it, producedbetter results than training a deblurring network on noisy images.Numerous tests demonstrate that this cascaded network performscompetitively in terms of PSNR and SSIM.","manuscriptTitle":"A Cascaded Convolutional Neural Network for Image Deblurring and Denoising","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2022-12-28 11:35:58","doi":"10.21203/rs.3.rs-2395895/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"0584f49b-203c-4846-b7a4-59766791a4d9","owner":[],"postedDate":"December 28th, 2022","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2023-03-28T14:14:27+00:00","versionOfRecord":[],"versionCreatedAt":"2022-12-28 11:35:58","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-2395895","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-2395895","identity":"rs-2395895","version":["v1"]},"buildId":"WrCJVZZCHTDjtuVLN7oU0","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}