Non-Reference Enhanced Low-Light Image Estimation Using Zero-DCE with Filtering Refinement.

Non-Reference Enhanced Low-Light Image Estimation Using Zero-DCE with Filtering Refinement. | 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 Non-Reference Enhanced Low-Light Image Estimation Using Zero-DCE with Filtering Refinement. Vijaya Maloth, Ravi Kumar Jatoth This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3835683/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 This paper introduces Modified Zero-Reference Deep Curve Estimation (Zero-DCE), a novel technique that treats light enhancement as image-specific curve estimation task using a deep curve network. Our network, powered by DCE-Net, trains a light-weight deep network to estimate pixel-wise and higher order curves, facilitating dynamic range adjustment in an images. The design of our curve estimation network prioritizes considerations such as pixel value range, differentiability, and monotonicity. An intriguing aspect of modified Zero-DCE lies in its departure from strict requirements on the reference images. It doesn't rely on unpaired or paired data during training. Instead, it leverages a set of meticulously crafted the non-reference loss functions. These loss functions implicitly evaluate image enhancement quality and guide the network's learning process. Despite its simplicity, our method demonstrates robust generalization across the diverse lighting conditions. To further refine enhanced images generated through this network, a post-processing step involves filtering to eliminate noise that emerges after transforming the low-light images into high-light ones. This noise reduction step significantly enhances images, resulting in remarkable improvements in SSIM (Structural Similarity Index) and PSNR (Peak Signal-to-Noise Ratio) metrics when comparing the de-noised enhanced images to their high-light images. Zero-Deep Curve Estimation(DCE) Non-reference Loss Functions Curve Estimation Noise Reduction Structural Similarity Index Measure (SSIM) and Peak Signal-to-Noise Ratio (PSNR). Full Text 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-3835683","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":278512450,"identity":"3b52b615-851e-453d-b9cc-368b1f2fe174","order_by":0,"name":"Vijaya Maloth","email":"data:image/png;base64,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","orcid":"https://orcid.org/0009-0004-3749-8081","institution":"National Institute of Technology Warangal","correspondingAuthor":true,"prefix":"","firstName":"Vijaya","middleName":"","lastName":"Maloth","suffix":""},{"id":278512451,"identity":"0f0bb3f3-f6ab-4e3b-924f-b9177be5e00c","order_by":1,"name":"Ravi Kumar Jatoth","email":"","orcid":"","institution":"NIT Warangal: National Institute of Technology Warangal","correspondingAuthor":false,"prefix":"","firstName":"Ravi","middleName":"Kumar","lastName":"Jatoth","suffix":""}],"badges":[],"createdAt":"2024-01-05 00:28:27","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3835683/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3835683/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":54720221,"identity":"c76f7740-da99-46d1-8e34-882e2ac0a748","added_by":"auto","created_at":"2024-04-15 17:11:45","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":630997,"visible":true,"origin":"","legend":"","description":"","filename":"vijaya11.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3835683/v1_covered_282ac97d-e7fa-43ce-8d06-bc0a199424b9.pdf"}],"financialInterests":"","formattedTitle":"Non-Reference Enhanced Low-Light Image Estimation Using Zero-DCE with Filtering Refinement.","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":"Zero-Deep Curve Estimation(DCE), Non-reference Loss Functions, Curve Estimation, Noise Reduction, Structural Similarity Index Measure (SSIM) and Peak Signal-to-Noise Ratio (PSNR).","lastPublishedDoi":"10.21203/rs.3.rs-3835683/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3835683/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"This paper introduces Modified Zero-Reference Deep Curve Estimation (Zero-DCE), a novel technique that treats light enhancement as image-specific curve estimation task using a deep curve network. Our network, powered by DCE-Net, trains a light-weight deep network to estimate pixel-wise and higher order curves, facilitating dynamic range adjustment in an images. The design of our curve estimation network prioritizes considerations such as pixel value range, differentiability, and monotonicity. An intriguing aspect of modified Zero-DCE lies in its departure from strict requirements on the reference images. It doesn't rely on unpaired or paired data during training. Instead, it leverages a set of meticulously crafted the non-reference loss functions. These loss functions implicitly evaluate image enhancement quality and guide the network's learning process. Despite its simplicity, our method demonstrates robust generalization across the diverse lighting conditions. To further refine enhanced images generated through this network, a post-processing step involves filtering to eliminate noise that emerges after transforming the low-light images into high-light ones. This noise reduction step significantly enhances images, resulting in remarkable improvements in SSIM (Structural Similarity Index) and PSNR (Peak Signal-to-Noise Ratio) metrics when comparing the de-noised enhanced images to their high-light images.","manuscriptTitle":"Non-Reference Enhanced Low-Light Image Estimation Using Zero-DCE with Filtering Refinement.","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-03-13 07:22:32","doi":"10.21203/rs.3.rs-3835683/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":"7d02e6af-8aa1-4fa6-9ae8-478de27f23bd","owner":[],"postedDate":"March 13th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-04-15T17:03:37+00:00","versionOfRecord":[],"versionCreatedAt":"2024-03-13 07:22:32","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-3835683","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3835683","identity":"rs-3835683","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}