CDMM:Conditional Diffusion Model with Mamba for Low-light Underwater Image Enhancement

CDMM:Conditional Diffusion Model with Mamba for Low-light Underwater Image Enhancement | 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 CDMM:Conditional Diffusion Model with Mamba for Low-light Underwater Image Enhancement Jianhua Zheng, Junde Lu, Ruolin Zhao, Yusha Fu, Jinfang Liu, Zhaoxi Luo, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6525447/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 19 You are reading this latest preprint version Abstract Underwater photography is frequently characterized by low contrast, blurred edge details, and color distortions, primarily due to inadequate lighting. These factors impede the acquisition and analysis of underwater imagery using computer vision techniques. In the domain of improving visibility in underwater images taken under dim lighting, existing studies usually result in the introduction of artifacts, the loss of edge details, and an increase in noise. This research introduces a novel approach grounded in a diffusion model intended to optimize the quality of underwater imagery taken in dim conditions, utilizing low-light images and Gaussian noise as inputs to produce enhanced outputs. To enhance the denoising process within the diffusion model, a TCM-Block has been integrated as the denoising component, thus elevating the quality of the resultant images. Furthermore, the diffusion process is guided by the original image to preserve edge details and enhance visual perception. The experimental results indicate that our approach surpasses eight alternative methods in six metrics ranks second in the seventh, and exhibits strong performance on images with varying degrees of low-light conditions, highlighting the considerable advantages of our approach. This study not only provides an effective technical solution for enhancing low-light underwater images but also presents a novel perspective on image processing in such environments, facilitated by the application of the diffusion model and the Mamba block. Deep learning Low-light underwater image enhancement Diffusion Model Mamba Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 14 Aug, 2025 Reviews received at journal 13 Aug, 2025 Reviews received at journal 08 Aug, 2025 Reviewers agreed at journal 05 Aug, 2025 Reviewers agreed at journal 04 Aug, 2025 Reviewers agreed at journal 04 Aug, 2025 Reviews received at journal 04 Aug, 2025 Reviewers agreed at journal 04 Aug, 2025 Reviewers agreed at journal 03 Aug, 2025 Reviewers agreed at journal 03 Aug, 2025 Reviewers agreed at journal 03 Aug, 2025 Reviews received at journal 02 Aug, 2025 Reviewers agreed at journal 02 Aug, 2025 Reviewers agreed at journal 02 Aug, 2025 Reviewers agreed at journal 02 Aug, 2025 Reviewers invited by journal 02 Aug, 2025 Editor assigned by journal 02 Aug, 2025 Submission checks completed at journal 26 Apr, 2025 First submitted to journal 25 Apr, 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-6525447","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":497387598,"identity":"8ccbbf96-74e7-4b9b-a109-ca3bcdb3884a","order_by":0,"name":"Jianhua Zheng","email":"","orcid":"","institution":"Zhongkai University of Agriculture and Engineering","correspondingAuthor":false,"prefix":"","firstName":"Jianhua","middleName":"","lastName":"Zheng","suffix":""},{"id":497387599,"identity":"d49c3584-dcc1-44b1-a835-e75f9b832afd","order_by":1,"name":"Junde Lu","email":"","orcid":"","institution":"Zhongkai University of Agriculture and Engineering","correspondingAuthor":false,"prefix":"","firstName":"Junde","middleName":"","lastName":"Lu","suffix":""},{"id":497387600,"identity":"1c38e46f-8e10-447e-8c64-f50ae61fe5e3","order_by":2,"name":"Ruolin Zhao","email":"","orcid":"","institution":"Zhongkai University of Agriculture and Engineering","correspondingAuthor":false,"prefix":"","firstName":"Ruolin","middleName":"","lastName":"Zhao","suffix":""},{"id":497387601,"identity":"3abf7737-2260-49ea-97fe-4ba9dbcabbbc","order_by":3,"name":"Yusha Fu","email":"","orcid":"","institution":"Zhongkai University of Agriculture and Engineering","correspondingAuthor":false,"prefix":"","firstName":"Yusha","middleName":"","lastName":"Fu","suffix":""},{"id":497387602,"identity":"937002e6-53d6-4644-b37d-205f78282903","order_by":4,"name":"Jinfang Liu","email":"","orcid":"","institution":"Zhongkai University of Agriculture and Engineering","correspondingAuthor":false,"prefix":"","firstName":"Jinfang","middleName":"","lastName":"Liu","suffix":""},{"id":497387603,"identity":"af5b1df5-e468-4d66-97b3-59146a53b6aa","order_by":5,"name":"Zhaoxi Luo","email":"","orcid":"","institution":"Zhongkai University of Agriculture and Engineering","correspondingAuthor":false,"prefix":"","firstName":"Zhaoxi","middleName":"","lastName":"Luo","suffix":""},{"id":497387604,"identity":"c3c85f87-c42d-4bc1-bde5-5e1322e29ad2","order_by":6,"name":"Xiaomin Li","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA3klEQVRIiWNgGAWjYBACPmYGhgNAmoeBvYGNsQEkdICAFja4Fp4DxGqBsyQSiNXCzmN44EfFNhlzyefPHs5sY5Dju5HA+LkAr8PYEg72nLnNYzk7Id1wYxuDseSNBGbpGXi1MB84wNt2m8fgdsIxyYdtDIkbbiSwMfPg1cLYcPAvSMvNg20gLfVEaGE+cBhsyw1mNkmgwxIMCGthSzgsA/SLwZk0NskZ5yQMZ5552CyNTws//xnjj28qbtsbHD/+TLKnzEae73jywc/4tKADCSCGRM8oGAWjYBSMAgoAAPs/Seve+NDXAAAAAElFTkSuQmCC","orcid":"","institution":"Zhongkai University of Agriculture and Engineering","correspondingAuthor":true,"prefix":"","firstName":"Xiaomin","middleName":"","lastName":"Li","suffix":""}],"badges":[],"createdAt":"2025-04-25 05:23:27","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6525447/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6525447/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":88579554,"identity":"45f10208-7efb-42f3-9e51-d395772fda85","added_by":"auto","created_at":"2025-08-08 02:39:51","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1521155,"visible":true,"origin":"","legend":"","description":"","filename":"ConditionalDiffusionModelwithMambaforLowlightUnderwaterImageEnhancement.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6525447/v1_covered_6914be6c-0b14-403d-b1fd-5fe26c56c069.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"CDMM:Conditional Diffusion Model with Mamba for Low-light Underwater Image Enhancement","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":"the-journal-of-supercomputing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [The Journal of Supercomputing](https://www.springer.com/journal/11227)","snPcode":"11227","submissionUrl":"https://submission.nature.com/new-submission/11227/3","title":"The Journal of Supercomputing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Deep learning, Low-light underwater image enhancement, Diffusion Model, Mamba","lastPublishedDoi":"10.21203/rs.3.rs-6525447/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6525447/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eUnderwater photography is frequently characterized by low contrast, blurred edge details, and color distortions, primarily due to inadequate lighting. These factors impede the acquisition and analysis of underwater imagery using computer vision techniques. In the domain of improving visibility in underwater images taken under dim lighting, existing studies usually result in the introduction of artifacts, the loss of edge details, and an increase in noise. This research introduces a novel approach grounded in a diffusion model intended to optimize the quality of underwater imagery taken in dim conditions, utilizing low-light images and Gaussian noise as inputs to produce enhanced outputs. To enhance the denoising process within the diffusion model, a TCM-Block has been integrated as the denoising component, thus elevating the quality of the resultant images. Furthermore, the diffusion process is guided by the original image to preserve edge details and enhance visual perception. The experimental results indicate that our approach surpasses eight alternative methods in six metrics ranks second in the seventh, and exhibits strong performance on images with varying degrees of low-light conditions, highlighting the considerable advantages of our approach. This study not only provides an effective technical solution for enhancing low-light underwater images but also presents a novel perspective on image processing in such environments, facilitated by the application of the diffusion model and the Mamba block.\u003c/p\u003e","manuscriptTitle":"CDMM:Conditional Diffusion Model with Mamba for Low-light Underwater Image Enhancement","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-08 02:23:34","doi":"10.21203/rs.3.rs-6525447/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-08-14T21:23:54+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-08-13T06:19:25+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-08-08T08:22:09+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"92267698687425852438915863376627499303","date":"2025-08-05T14:47:40+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"206507704400886762623381877166357333558","date":"2025-08-05T01:49:18+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"143631716906922517410272568904351337220","date":"2025-08-04T14:33:58+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-08-04T09:15:40+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"139074454089552057988549562855931394409","date":"2025-08-04T07:56:58+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"264690911417925930331000352255711331207","date":"2025-08-04T02:02:12+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"203531118744457035577471939040348355901","date":"2025-08-03T12:42:27+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"269376586661533213169110091636090557443","date":"2025-08-03T10:01:13+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-08-02T22:39:09+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"31409568779836083269085217781477038740","date":"2025-08-02T22:10:20+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"115344802952277599818399539788895995963","date":"2025-08-02T15:35:53+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"305822249868931279467758019290318239675","date":"2025-08-02T14:34:08+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-08-02T14:31:25+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-08-02T14:04:05+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-04-26T20:39:56+00:00","index":"","fulltext":""},{"type":"submitted","content":"The Journal of Supercomputing","date":"2025-04-25T05:16:01+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"the-journal-of-supercomputing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [The Journal of Supercomputing](https://www.springer.com/journal/11227)","snPcode":"11227","submissionUrl":"https://submission.nature.com/new-submission/11227/3","title":"The Journal of Supercomputing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"e6ef37bb-7298-43de-bc74-f4ccd466baa1","owner":[],"postedDate":"August 8th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2025-10-13T16:23:28+00:00","versionOfRecord":[],"versionCreatedAt":"2025-08-08 02:23:34","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6525447","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6525447","identity":"rs-6525447","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}