Remote Sensing Image Super-Resolution Reconstruction by Fusing Multi-Scale Receptive Fields and Hybrid Transformer

Remote Sensing Image Super-Resolution Reconstruction by Fusing Multi-Scale Receptive Fields and Hybrid Transformer | 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 Article Remote Sensing Image Super-Resolution Reconstruction by Fusing Multi-Scale Receptive Fields and Hybrid Transformer Denghui Liu, Lin Zhong, Haiyang Wu, Songyang Li, Yida Li This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5223288/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 16 Jan, 2025 Read the published version in Scientific Reports → Version 1 posted 12 You are reading this latest preprint version Abstract To enhance high-frequency perceptual information and texture details in remote sensing images and address the challenges of super-resolution reconstruction algorithms during training, particularly the issue of missing details, this paper proposes an improved remote sensing image super-resolution reconstruction model. The generator network of the model employs multi-scale convolutional kernels to extract image features and utilizes a multi-head self-attention mechanism to dynamically fuse these features, significantly improving the ability to capture both fine details and global information in remote sensing images. Additionally, the model introduces a multi-stage Hybrid Transformer structure, which processes features at different resolutions progressively, from low resolution to high resolution, substantially enhancing reconstruction quality and detail recovery. The discriminator combines multi-scale convolution, global Transformer, and hierarchical feature discriminators, providing a comprehensive and refined evaluation of image quality. Finally, the model incorporates a Charbonnier loss function and total variation (TV) loss function, which significantly improve training stability and accelerate convergence. Experimental results demonstrate that the proposed method, compared to the SRGAN algorithm, achieves average improvements of approximately 3.61 dB in Peak Signal-to-Noise Ratio (PSNR), 0.070 (8.2%) in Structural Similarity Index (SSIM), and 0.030 (3.1%) in Feature Similarity Index (FSIM) across multiple datasets, showing significant performance gains. Physical sciences/Mathematics and computing/Computer science Physical sciences/Mathematics and computing/Information technology Physical sciences/Engineering/Aerospace engineering Remote Sensing Image Image Super-Resolution GAN Attention Mechanism Hybrid Transformer Multi-Scale Feature Extraction Comprehensive Discriminator Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 16 Jan, 2025 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 24 Nov, 2024 Reviews received at journal 17 Nov, 2024 Reviews received at journal 14 Nov, 2024 Reviews received at journal 11 Nov, 2024 Reviewers agreed at journal 02 Nov, 2024 Reviewers agreed at journal 01 Nov, 2024 Reviewers agreed at journal 01 Nov, 2024 Reviewers invited by journal 01 Nov, 2024 Editor assigned by journal 31 Oct, 2024 Editor invited by journal 30 Oct, 2024 Submission checks completed at journal 28 Oct, 2024 First submitted to journal 08 Oct, 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-5223288","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":382067917,"identity":"a6288088-4ff0-4b12-a216-de7c9deb13d7","order_by":0,"name":"Denghui Liu","email":"","orcid":"","institution":"Xijing University","correspondingAuthor":false,"prefix":"","firstName":"Denghui","middleName":"","lastName":"Liu","suffix":""},{"id":382067918,"identity":"e8f55d56-619d-47a2-ab54-5d1890b9c3c8","order_by":1,"name":"Lin Zhong","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA2UlEQVRIiWNgGAWjYDACCQiVwMDAfPBBQkUNSVrYkg0enDlGkhYeM8mHLcyEdcjPbj728AuDXR6/dINZRWIDGwN/e3cCXi2Mc46lG8swJBdLzjmQdiNxhwyDxJmzG/BqYZbIMZOWYDiQuOFGwrEbiWfYGAwkcvFrYYNp2X8jsa0gsY2ZsBYeoBbJDyBbJJLZGIjSIiGRlibNwJCcOONGGrNEwpljPAT9Ij8j+ZjkDwa7xP4Z+R8//qiokeNv78WvBQSYef8huZSgchBg/EGUslEwCkbBKBixAADyHUW+HV9qOgAAAABJRU5ErkJggg==","orcid":"","institution":"Xijing University","correspondingAuthor":true,"prefix":"","firstName":"Lin","middleName":"","lastName":"Zhong","suffix":""},{"id":382067919,"identity":"e3ed44d1-1e96-405a-84e3-81eaf84fd054","order_by":2,"name":"Haiyang Wu","email":"","orcid":"","institution":"Xijing University","correspondingAuthor":false,"prefix":"","firstName":"Haiyang","middleName":"","lastName":"Wu","suffix":""},{"id":382067920,"identity":"a7d694f0-fb90-42de-a421-7397b9fda489","order_by":3,"name":"Songyang Li","email":"","orcid":"","institution":"Xijing University","correspondingAuthor":false,"prefix":"","firstName":"Songyang","middleName":"","lastName":"Li","suffix":""},{"id":382067921,"identity":"5d1979c8-f4a9-4b2d-8af0-ae599217e922","order_by":4,"name":"Yida Li","email":"","orcid":"","institution":"Xijing University","correspondingAuthor":false,"prefix":"","firstName":"Yida","middleName":"","lastName":"Li","suffix":""}],"badges":[],"createdAt":"2024-10-08 08:23:07","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5223288/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5223288/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-025-86446-5","type":"published","date":"2025-01-16T15:57:34+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":74284847,"identity":"426e686e-c85f-49d0-9be4-5e6a9b477d4a","added_by":"auto","created_at":"2025-01-20 16:13:03","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":884948,"visible":true,"origin":"","legend":"","description":"","filename":"RemoteSensingImageSuperResolutionReconstructionbyFusingMultiScaleReceptiveFieldsandHybridTransformer.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5223288/v1_covered_56fb295a-8037-4717-aaf3-5842013cbbec.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Remote Sensing Image Super-Resolution Reconstruction by Fusing Multi-Scale Receptive Fields and Hybrid Transformer","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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Remote Sensing Image, Image Super-Resolution, GAN, Attention Mechanism, Hybrid Transformer, Multi-Scale Feature Extraction, Comprehensive Discriminator","lastPublishedDoi":"10.21203/rs.3.rs-5223288/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5223288/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eTo enhance high-frequency perceptual information and texture details in remote sensing images and address the challenges of super-resolution reconstruction algorithms during training, particularly the issue of missing details, this paper proposes an improved remote sensing image super-resolution reconstruction model. The generator network of the model employs multi-scale convolutional kernels to extract image features and utilizes a multi-head self-attention mechanism to dynamically fuse these features, significantly improving the ability to capture both fine details and global information in remote sensing images. Additionally, the model introduces a multi-stage Hybrid Transformer structure, which processes features at different resolutions progressively, from low resolution to high resolution, substantially enhancing reconstruction quality and detail recovery. The discriminator combines multi-scale convolution, global Transformer, and hierarchical feature discriminators, providing a comprehensive and refined evaluation of image quality. Finally, the model incorporates a Charbonnier loss function and total variation (TV) loss function, which significantly improve training stability and accelerate convergence. Experimental results demonstrate that the proposed method, compared to the SRGAN algorithm, achieves average improvements of approximately 3.61 dB in Peak Signal-to-Noise Ratio (PSNR), 0.070 (8.2%) in Structural Similarity Index (SSIM), and 0.030 (3.1%) in Feature Similarity Index (FSIM) across multiple datasets, showing significant performance gains.\u003c/p\u003e","manuscriptTitle":"Remote Sensing Image Super-Resolution Reconstruction by Fusing Multi-Scale Receptive Fields and Hybrid Transformer","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-12-17 11:41:56","doi":"10.21203/rs.3.rs-5223288/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-11-25T03:52:58+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-11-17T13:17:26+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-11-14T11:59:00+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-11-11T11:41:52+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"57568453664528912608833558160087068199","date":"2024-11-02T12:07:41+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"291138726405751736687789106074567383928","date":"2024-11-01T13:28:08+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"60197941574861474167537632835556485013","date":"2024-11-01T09:20:52+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-11-01T09:11:13+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-10-31T18:41:20+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2024-10-30T10:21:13+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-10-28T08:14:48+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2024-10-08T08:07:44+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"bb3182b2-ab4b-4bc6-9295-108782637482","owner":[],"postedDate":"December 17th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":40686190,"name":"Physical sciences/Mathematics and computing/Computer science"},{"id":40686191,"name":"Physical sciences/Mathematics and computing/Information technology"},{"id":40686192,"name":"Physical sciences/Engineering/Aerospace engineering"}],"tags":[],"updatedAt":"2025-01-20T16:06:25+00:00","versionOfRecord":{"articleIdentity":"rs-5223288","link":"https://doi.org/10.1038/s41598-025-86446-5","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2025-01-16 15:57:34","publishedOnDateReadable":"January 16th, 2025"},"versionCreatedAt":"2024-12-17 11:41:56","video":"","vorDoi":"10.1038/s41598-025-86446-5","vorDoiUrl":"https://doi.org/10.1038/s41598-025-86446-5","workflowStages":[]},"version":"v1","identity":"rs-5223288","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5223288","identity":"rs-5223288","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}