A Low-Light Image Enhancement Algorithm Based on Improved Pyramid Diffusion Model 

A Low-Light Image Enhancement Algorithm Based on Improved Pyramid Diffusion Model | 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 Low-Light Image Enhancement Algorithm Based on Improved Pyramid Diffusion Model Xin Hu, Jinhua Wang, Ning He, Donghui Wang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4387487/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 9 You are reading this latest preprint version Abstract Images captured in low-light conditions often suffer from poor visibility, high noise levels, and significant detail loss. These issues can severely hinder subsequent visual tasks like object detection and facial recognition. Therefore, low-light image enhancement is a crucial yet challenging problem in computer vision, aiming to recover high-quality images.Pyramid-based Diffusion Model, a type of generative model capable of modeling and generating high-dimensional data distributions, have recently been explored for low-light image enhancement. However, a common limitation of diffusion models is the potential loss of detail in small areas due to the forward noising and reverse denoising process. To address this, the proposed algorithm integrates a novel attention mechanism that progressively utilizes depthwise separable convolution units with expanding convolutional kernels. This approach effectively enhances the network's ability to handle larger receptive fields, leading to better detail preservation. Furthermore, the algorithm incorporates a dual interpolation sampling method for improved detail recovery. Additionally, a new combination optimization model for loss functions is adopted. Experimental results demonstrate that the proposed method outperforms the baseline network (which lacks color correction methods) on both subjective and objective evaluation metrics across LOL-v1, LOL-v2, and other unpaired datasets. This performance surpasses current mainstream low-light enhancement algorithms. Low-light image enhancement methods Diffusion model Transformer Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 14 Jun, 2024 Reviewers agreed at journal 02 Jun, 2024 Reviews received at journal 23 May, 2024 Reviewers agreed at journal 11 May, 2024 Reviewers agreed at journal 10 May, 2024 Reviewers invited by journal 10 May, 2024 Editor assigned by journal 09 May, 2024 Submission checks completed at journal 09 May, 2024 First submitted to journal 08 May, 2024 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-4387487","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":301289654,"identity":"f2d0d46f-1379-441b-9504-16d7a767d0b4","order_by":0,"name":"Xin Hu","email":"","orcid":"","institution":"Beijing Union University","correspondingAuthor":false,"prefix":"","firstName":"Xin","middleName":"","lastName":"Hu","suffix":""},{"id":301289655,"identity":"b9b05198-e848-43c9-a8d4-8787eb6e655f","order_by":1,"name":"Jinhua Wang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA9klEQVRIiWNgGAWjYBADZjYGHiBVcQDMkyCgGFnLGRK0AAFQC2MbEVoMbuQfk/i5o5adT7oXyJh3J3HDAeaDt3kY7PJwaZHsOcwm2XvmODObzLk0yd5tz4Ba2JKteRiSi3Fp4WdvZrvB23aMmU0ix0yCd9thoBYeM2kehgOJDTi0sDEzs938C9Ui+XcOSAv/N7xaQLbc5m2rAWuR5m0A28KGVwvQL+a/ZdsOgLQYW8sce2Y88zCbseUcg2ScWgxuJD42fNtWlyw/I8fw5puaO7J9x5sf3nhTYYdTCxQcTkawwRFlgF89ENTZEVQyCkbBKBgFIxcAADGVVLNgykGmAAAAAElFTkSuQmCC","orcid":"","institution":"Beijing Union University","correspondingAuthor":true,"prefix":"","firstName":"Jinhua","middleName":"","lastName":"Wang","suffix":""},{"id":301289656,"identity":"bbdaf0b5-5250-4df0-a16a-47d53b2ec4fb","order_by":2,"name":"Ning He","email":"","orcid":"","institution":"Beijing Union University","correspondingAuthor":false,"prefix":"","firstName":"Ning","middleName":"","lastName":"He","suffix":""},{"id":301289657,"identity":"30eb4403-0dfe-4197-ab50-708eb7dee05d","order_by":3,"name":"Donghui Wang","email":"","orcid":"","institution":"Beijing Union University","correspondingAuthor":false,"prefix":"","firstName":"Donghui","middleName":"","lastName":"Wang","suffix":""}],"badges":[],"createdAt":"2024-05-08 07:55:50","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4387487/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4387487/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":56858735,"identity":"3ff3fa73-05b7-4e4f-83f3-d599a1eeb3d4","added_by":"auto","created_at":"2024-05-21 10:47:40","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1208918,"visible":true,"origin":"","legend":"","description":"","filename":"ArticleTitle.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4387487/v1_covered_ed1dd219-de38-4764-8571-ca76dcee3112.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Low-Light Image Enhancement Algorithm Based on Improved Pyramid Diffusion Model ","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":"multimedia-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mmsj","sideBox":"Learn more about [Multimedia Systems](http://link.springer.com/journal/530)","snPcode":"530","submissionUrl":"https://submission.nature.com/new-submission/530/3","title":"Multimedia Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Low-light image enhancement methods, Diffusion model, Transformer","lastPublishedDoi":"10.21203/rs.3.rs-4387487/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4387487/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Images captured in low-light conditions often suffer from poor visibility, high noise levels, and significant detail loss. These issues can severely hinder subsequent visual tasks like object detection and facial recognition. Therefore, low-light image enhancement is a crucial yet challenging problem in computer vision, aiming to recover high-quality images.Pyramid-based Diffusion Model, a type of generative model capable of modeling and generating high-dimensional data distributions, have recently been explored for low-light image enhancement. However, a common limitation of diffusion models is the potential loss of detail in small areas due to the forward noising and reverse denoising process. To address this, the proposed algorithm integrates a novel attention mechanism that progressively utilizes depthwise separable convolution units with expanding convolutional kernels. This approach effectively enhances the network's ability to handle larger receptive fields, leading to better detail preservation. Furthermore, the algorithm incorporates a dual interpolation sampling method for improved detail recovery. Additionally, a new combination optimization model for loss functions is adopted. Experimental results demonstrate that the proposed method outperforms the baseline network (which lacks color correction methods) on both subjective and objective evaluation metrics across LOL-v1, LOL-v2, and other unpaired datasets. This performance surpasses current mainstream low-light enhancement algorithms.","manuscriptTitle":"A Low-Light Image Enhancement Algorithm Based on Improved Pyramid Diffusion Model ","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-05-21 10:39:32","doi":"10.21203/rs.3.rs-4387487/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2024-06-14T08:17:56+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"102198874574866924151648913376670167145","date":"2024-06-03T01:50:37+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-05-23T12:42:56+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"182501712040799543644290469350780128085","date":"2024-05-11T08:31:08+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"281267027430058287221259316082313666319","date":"2024-05-11T02:38:33+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-05-11T02:36:30+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-05-09T16:22:58+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-05-09T14:12:13+00:00","index":"","fulltext":""},{"type":"submitted","content":"Multimedia Systems","date":"2024-05-08T07:53:15+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"multimedia-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mmsj","sideBox":"Learn more about [Multimedia Systems](http://link.springer.com/journal/530)","snPcode":"530","submissionUrl":"https://submission.nature.com/new-submission/530/3","title":"Multimedia Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"a8dec472-7472-4911-93f5-8dcb7ea9da51","owner":[],"postedDate":"May 21st, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2024-05-21T10:39:32+00:00","versionOfRecord":[],"versionCreatedAt":"2024-05-21 10:39:32","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4387487","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4387487","identity":"rs-4387487","version":["v1"]},"buildId":"J0_U0BvcaRcwD8yVFaRlm","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}