Super-Resolution Reconstruction of Remote Sensing Images Using Generative Adversarial Network with Permuted Self-Attention

Super-Resolution Reconstruction of Remote Sensing Images Using Generative Adversarial Network with Permuted Self-Attention | 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 Super-Resolution Reconstruction of Remote Sensing Images Using Generative Adversarial Network with Permuted Self-Attention Bin Yin, Xin Mu, Hongwei Zhang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7913261/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 Image super-resolution (SR) reconstruction plays a key role in meeting the ever-growing demand for high-spatial-resolution remote-sensing imagery. Although generative adversarial networks (GANs) have been widely adopted for SR, their dependence on high-frequency information learned from training data often produces artifacts or distortions in complex remote-sensing scenes. Optical satellite images exhibit more intricate spatial distributions and richer multi-scale ground features than natural images; therefore, directly applying existing SR methods to them usually causes unstable convergence and noticeable visual artifacts, seriously degrading reconstruction quality and usability. To address these issues, we propose an improved GAN-based SR network that embeds a Permuted Self-Attention (PSA) module to strengthen global modeling. The PSA module employs a global-context-aware mechanism to adaptively select useful information and suppress noise, markedly improving the reconstruction of multi-scale objects in remote-sensing images. Extensive experiments on standard remote-sensing datasets demonstrate that the proposed method outperforms state-of-the-art alternatives in both objective metrics (PSNR, SSIM) and subjective visual quality, confirming its robustness and effectiveness in complex remote-sensing scenarios. Physical sciences/Engineering Physical sciences/Mathematics and computing Physical sciences/Optics and photonics Generative adversarial network remote-sensing images super-resolution 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-7913261","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":544218893,"identity":"5a738a03-987b-4a0c-b749-6a0a20e34d0d","order_by":0,"name":"Bin Yin","email":"","orcid":"","institution":"Changchun University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Bin","middleName":"","lastName":"Yin","suffix":""},{"id":544218894,"identity":"02790c61-ba05-45fb-ba43-cdee5f5e6899","order_by":1,"name":"Xin Mu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA0klEQVRIiWNgGAWjYJCCAwwGNnKMzewHHyRU1BCrpSDNmLm9J9ngwZljxNrz4XBie88BM8mHLcyEFevOyDE8XGBw2Jh3RkJaRWIDGwN/e3cCXi1mN9ISDs8wSJeTnJF47EbiDhkGiTNnNxDQknzgMI+BtbEh0JYbiWfYGAwkcglpSWwAamFO3H8jwawgsY2ZGC1gW5wTG4HeZyBOy5lnCUAtacaMwECWSDhzjIewX47nGH/m+QOJyo8/Kmrk+Nt78WvBADykKR8Fo2AUjIJRgBUAAKQJT2N6RdKpAAAAAElFTkSuQmCC","orcid":"","institution":"Changchun University of Technology","correspondingAuthor":true,"prefix":"","firstName":"Xin","middleName":"","lastName":"Mu","suffix":""},{"id":544218895,"identity":"3eaaaef4-ce49-4350-9bda-04792cfbf4c9","order_by":2,"name":"Hongwei Zhang","email":"","orcid":"","institution":"Changchun University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Hongwei","middleName":"","lastName":"Zhang","suffix":""}],"badges":[],"createdAt":"2025-10-21 10:14:45","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7913261/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7913261/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":96607819,"identity":"edfd046b-c067-4446-9e9d-fa5347e58b90","added_by":"auto","created_at":"2025-11-24 09:27:48","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":8987196,"visible":true,"origin":"","legend":"","description":"","filename":"PSAESRGAN.docx","url":"https://assets-eu.researchsquare.com/files/rs-7913261/v1/5c6d0db26a3ef877d7560a86.docx"},{"id":96607797,"identity":"2ca53eb1-9aaf-47e7-9de1-156df4d7b9d7","added_by":"auto","created_at":"2025-11-24 09:27:46","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5603,"visible":true,"origin":"","legend":"","description":"","filename":"b9f1194def6449769b7e9d3c233d4687.json","url":"https://assets-eu.researchsquare.com/files/rs-7913261/v1/b340c0cb5635db008a8b0476.json"},{"id":96607784,"identity":"3bd3dd4a-c53d-4e98-b34a-3ef1f64a7fa4","added_by":"auto","created_at":"2025-11-24 09:27:44","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":89191,"visible":true,"origin":"","legend":"","description":"","filename":"b9f1194def6449769b7e9d3c233d46871enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7913261/v1/d8393f8c94e3ee1d734fe55e.xml"},{"id":96607788,"identity":"d0978de4-1149-425c-99f2-beaaa1ca50d1","added_by":"auto","created_at":"2025-11-24 09:27:44","extension":"jpeg","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":168943,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7913261/v1/f53b918c46684762a0ecfab0.jpeg"},{"id":96607817,"identity":"88ecbfe1-0ab4-4bd0-abd4-3eddb997402f","added_by":"auto","created_at":"2025-11-24 09:27:48","extension":"jpeg","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":277124,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7913261/v1/b6024e2c423e539371cdbc21.jpeg"},{"id":96607822,"identity":"7cc45ea6-8ab1-4af8-baa0-4182e9a54327","added_by":"auto","created_at":"2025-11-24 09:27:49","extension":"jpeg","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":216066,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7913261/v1/a54467921caa9fece21424e8.jpeg"},{"id":96607829,"identity":"b3de3d1c-cf84-4ee6-8774-d9b22a52cd20","added_by":"auto","created_at":"2025-11-24 09:27:50","extension":"emf","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":210820,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.emf","url":"https://assets-eu.researchsquare.com/files/rs-7913261/v1/13ea127eea02d3e629a58968.emf"},{"id":96607732,"identity":"39291692-cd09-4f65-a9d7-4b057e3956a8","added_by":"auto","created_at":"2025-11-24 09:27:34","extension":"jpeg","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":963858,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7913261/v1/8c47f640d5edf5a43fc30813.jpeg"},{"id":96607730,"identity":"c2508bb6-53ca-45c9-a4e0-7244a511d059","added_by":"auto","created_at":"2025-11-24 09:27:34","extension":"emf","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1753848,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage6.emf","url":"https://assets-eu.researchsquare.com/files/rs-7913261/v1/e7d298640f9a5441e83629e5.emf"},{"id":96607767,"identity":"562db1ad-b1c5-4104-92f0-7b7b04c78d25","added_by":"auto","created_at":"2025-11-24 09:27:41","extension":"jpeg","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":784570,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage7.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7913261/v1/2111f83ca8dfd13a554ad134.jpeg"},{"id":96607753,"identity":"83e9cf58-3eec-46ae-9928-5af5558cf1a5","added_by":"auto","created_at":"2025-11-24 09:27:38","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":55059,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7913261/v1/904a50d92d61b6ca55188bfb.png"},{"id":96607703,"identity":"01565067-288c-447d-b850-00e2acb56488","added_by":"auto","created_at":"2025-11-24 09:27:30","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":38117,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7913261/v1/ebb734ab4606fea614f759b7.png"},{"id":96607831,"identity":"7bb8184d-8ecc-4b99-84de-4063e83143d5","added_by":"auto","created_at":"2025-11-24 09:27:50","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":30825,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7913261/v1/3beec53096283286219a1900.png"},{"id":96607792,"identity":"13bee0ff-ed16-43d6-b15e-2c900bf68a09","added_by":"auto","created_at":"2025-11-24 09:27:46","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":8489,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7913261/v1/d7409342039321bb4859c1e3.png"},{"id":96607828,"identity":"45afd86d-b07a-4f26-972b-9e0003ec7b46","added_by":"auto","created_at":"2025-11-24 09:27:49","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":527868,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7913261/v1/218ab90e55f82d5e48cd85ef.png"},{"id":96607800,"identity":"61efac28-7088-4eb0-a52d-1f31c63f3453","added_by":"auto","created_at":"2025-11-24 09:27:46","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":198692,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7913261/v1/f24fa1fc4723eade6c1b822e.png"},{"id":96607820,"identity":"db9b3eaf-056a-49cc-9002-28a50ed9dd04","added_by":"auto","created_at":"2025-11-24 09:27:48","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":406094,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-7913261/v1/ad501a342987df05adc953d4.png"},{"id":96607830,"identity":"95e435d0-fc05-4019-a63f-49fa1d4e189c","added_by":"auto","created_at":"2025-11-24 09:27:50","extension":"xml","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":82034,"visible":true,"origin":"","legend":"","description":"","filename":"b9f1194def6449769b7e9d3c233d46871structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7913261/v1/2192c42a6ffa5552dd112d88.xml"},{"id":96607787,"identity":"c252b4ef-cbfa-48f7-a727-1b0f08595f99","added_by":"auto","created_at":"2025-11-24 09:27:44","extension":"html","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":98445,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7913261/v1/01b78f125036779d93933a61.html"},{"id":97142554,"identity":"ed6d613f-0696-4eb1-8e17-6515bb25bc77","added_by":"auto","created_at":"2025-12-01 10:07:43","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":711268,"visible":true,"origin":"","legend":"","description":"","filename":"PSAESRGAN.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7913261/v1_covered_79864ada-68d0-4657-816f-3d3c532fe659.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Super-Resolution Reconstruction of Remote Sensing Images Using Generative Adversarial Network with Permuted Self-Attention","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":"Generative adversarial network, remote-sensing images, super-resolution","lastPublishedDoi":"10.21203/rs.3.rs-7913261/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7913261/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eImage super-resolution (SR) reconstruction plays a key role in meeting the ever-growing demand for high-spatial-resolution remote-sensing imagery. Although generative adversarial networks (GANs) have been widely adopted for SR, their dependence on high-frequency information learned from training data often produces artifacts or distortions in complex remote-sensing scenes. Optical satellite images exhibit more intricate spatial distributions and richer multi-scale ground features than natural images; therefore, directly applying existing SR methods to them usually causes unstable convergence and noticeable visual artifacts, seriously degrading reconstruction quality and usability. To address these issues, we propose an improved GAN-based SR network that embeds a Permuted Self-Attention (PSA) module to strengthen global modeling. The PSA module employs a global-context-aware mechanism to adaptively select useful information and suppress noise, markedly improving the reconstruction of multi-scale objects in remote-sensing images. Extensive experiments on standard remote-sensing datasets demonstrate that the proposed method outperforms state-of-the-art alternatives in both objective metrics (PSNR, SSIM) and subjective visual quality, confirming its robustness and effectiveness in complex remote-sensing scenarios.\u003c/p\u003e","manuscriptTitle":"Super-Resolution Reconstruction of Remote Sensing Images Using Generative Adversarial Network with Permuted Self-Attention","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-22 17:29:00","doi":"10.21203/rs.3.rs-7913261/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":"17f0f0c0-7342-4fef-8a58-45233987dbbf","owner":[],"postedDate":"November 22nd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":57901751,"name":"Physical sciences/Engineering"},{"id":57901752,"name":"Physical sciences/Mathematics and computing"},{"id":57901753,"name":"Physical sciences/Optics and photonics"}],"tags":[],"updatedAt":"2025-12-01T06:24:02+00:00","versionOfRecord":[],"versionCreatedAt":"2025-11-22 17:29:00","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7913261","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7913261","identity":"rs-7913261","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}