PromptFFTNet: Prompt-Guided Hierarchical Transformer with FFT Attention for Single frame Atmospheric Turbulence removal

PromptFFTNet: Prompt-Guided Hierarchical Transformer with FFT Attention for Single frame Atmospheric Turbulence removal | 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 PromptFFTNet: Prompt-Guided Hierarchical Transformer with FFT Attention for Single frame Atmospheric Turbulence removal Muthukumar Balamurugan, Shivarama Holla K, Varun P. Gopi This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7468722/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 Atmospheric turbulence distorts images captured over long distances, blurring details and warping structures in unpredictable ways. Restoring a sharp, faithful scene from a single degraded frame remains a complex task caused by the absence of temporal information as well as the complex, non-uniform nature of the distortions. A novel single image atmospheric turbulence mitigation architecture is proposed, incorporating FFT-based window attention with prompt-conditioned hierarchical transformers for adaptive and fast restoration of degraded images. The proposed method computes frequency correlations through FFT to effectively capture long-range dependencies, unlike self-attention methods that scale poorly in terms of computation and offer limited global context. Extensive experiments on standard image restoration benchmarks demonstrate that Prompt-guided hierarchical transformer with FFT Attention Network (PromptFFTNet) achieves higher-quality restoration with less computation than existing methods. PromptFFTNet shows better performance than leading methods when evaluated by PSNR and SSIM, demonstrating high-quality image restoration and structural fidelity. This also implies that the restored images are more authentic and computationally practical, thus suitable for real-time applications. This makes PromptFFTNet a strong benchmark for removing atmospheric turbulence in images using FFT attention-based learning and prompt-conditioned restoration. Atmospheric Turbulence removal Fast Fourier Transform (FFT) Attention Block U shaped network (Unet) Encoder Transformer Decoder 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-7468722","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":509538385,"identity":"08761a7f-b12c-4890-8a3e-d28138005357","order_by":0,"name":"Muthukumar Balamurugan","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA50lEQVRIiWNgGAWjYHACNgjJ3nzgwAcwg6AOZogWPp5jiQ9ngLQwE6tFTiLH2JgHLEBAg+6M/GOPeSrs5Nh4zphJ2/zaJs/HzMD44WMObi1mN5LZjXnOJBuzsbeVSef23TZsY2Zglpy5Da8WNmnetgOJbTyHt0nn9txmBGphY+YlqOXfgfo2iQQzacue2/ZEamk4kMAmkWJszPDjdiJhLWcem0nOOZZs2AYK5N6G28ltzIzN+P1yPPGZxJsaO3n5dmBU/vhz23Z+e/PBDx/xaEEFjG1gsoFY9SDwhxTFo2AUjIJRMFIAABB9TZLok9vFAAAAAElFTkSuQmCC","orcid":"","institution":"Continental Autonomous Mobility (India) Pvt. Ltd","correspondingAuthor":true,"prefix":"","firstName":"Muthukumar","middleName":"","lastName":"Balamurugan","suffix":""},{"id":509538386,"identity":"6ffd1307-7a84-4402-9409-d1b411c259c7","order_by":1,"name":"Shivarama Holla K","email":"","orcid":"","institution":"Continental Autonomous Mobility (India) Pvt. Ltd","correspondingAuthor":false,"prefix":"","firstName":"Shivarama","middleName":"Holla","lastName":"K","suffix":""},{"id":509538387,"identity":"348c5c84-f944-45fa-9b32-7937584d9a1a","order_by":2,"name":"Varun P. Gopi","email":"","orcid":"","institution":"National Institute of Technology (NIT)","correspondingAuthor":false,"prefix":"","firstName":"Varun","middleName":"P.","lastName":"Gopi","suffix":""}],"badges":[],"createdAt":"2025-08-27 07:08:43","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7468722/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7468722/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":102634515,"identity":"443371cc-a5ac-4c4e-b29d-aa4f04831f0c","added_by":"auto","created_at":"2026-02-13 20:55:25","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1034622,"visible":true,"origin":"","legend":"","description":"","filename":"ManuScriptFinal.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7468722/v1_covered_787d3151-d640-4195-94e9-9e01f1038936.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"PromptFFTNet: Prompt-Guided Hierarchical Transformer with FFT Attention for Single frame Atmospheric Turbulence removal","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":"Atmospheric Turbulence removal, Fast Fourier Transform (FFT), Attention Block, U shaped network (Unet), Encoder, Transformer, Decoder","lastPublishedDoi":"10.21203/rs.3.rs-7468722/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7468722/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAtmospheric turbulence distorts images captured over long distances, blurring details and warping structures in unpredictable ways. Restoring a sharp, faithful scene from a single degraded frame remains a complex task caused by the absence of temporal information as well as the complex, non-uniform nature of the distortions. A novel single image atmospheric turbulence mitigation architecture is proposed, incorporating FFT-based window attention with prompt-conditioned hierarchical transformers for adaptive and fast restoration of degraded images. The proposed method computes frequency correlations through FFT to effectively capture long-range dependencies, unlike self-attention methods that scale poorly in terms of computation and offer limited global context. Extensive experiments on standard image restoration benchmarks demonstrate that Prompt-guided hierarchical transformer with FFT Attention Network (PromptFFTNet) achieves higher-quality restoration with less computation than existing methods. PromptFFTNet shows better performance than leading methods when evaluated by PSNR and SSIM, demonstrating high-quality image restoration and structural fidelity. This also implies that the restored images are more authentic and computationally practical, thus suitable for real-time applications. This makes PromptFFTNet a strong benchmark for removing atmospheric turbulence in images using FFT attention-based learning and prompt-conditioned restoration.\u003c/p\u003e","manuscriptTitle":"PromptFFTNet: Prompt-Guided Hierarchical Transformer with FFT Attention for Single frame Atmospheric Turbulence removal","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-09 19:47:16","doi":"10.21203/rs.3.rs-7468722/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":"bb3a1844-35fe-42d7-9aae-047af50c14c9","owner":[],"postedDate":"September 9th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-02-13T20:54:58+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-09 19:47:16","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7468722","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7468722","identity":"rs-7468722","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}