SWSformer: Sub-Window Shuffle Transformer for Image Restoration

SWSformer: Sub-Window Shuffle Transformer for Image Restoration | 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 SWSformer: Sub-Window Shuffle Transformer for Image Restoration Masato Shirai, Nagayuki Okitsu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5880999/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 Transformers have demonstrated superior performance over conventional methods in various tasks due to their ability to capture long-range dependencies and adaptively generate weights. However, their computational complexity increases quadratically with the number of tokens, limiting their applicability to high-resolution image tasks. Recent image restoration methods mitigate this by adopting mechanisms that sacrifice the ability to fully capture long-range dependencies. In contrast, Shuffle Transformer's window shuffle self-attention (WS-SA) is a mechanism that allows not only suppressing the computational complexity but also not restricting long-range dependency capture. Nevertheless, WS-SA has a problem that it causes a very sparse SA with a small receptive field for high-resolution images. In this work, we propose sub-window shuffle self-attention (SWS-SA), which is a mechanism to expand the receptive field without changing the computational complexity of WS-SA. In SWS-SA, the windows before shuffling are further partitioned into sub-windows, and shuffle is applied to them on a sub-window basis. After that, average pooling per sub-window is applied only to queries. Furthermore, we propose a Sub-Window Shuffle Transformer (SWSformer) that takes SWS-SA as its main mechanism and incorporates effective mechanisms proposed in related works. SWSformer achieves the same or better performance than state-of-the-art methods on denoising and deblurring tasks. Physical sciences/Mathematics and computing/Computer science Physical sciences/Mathematics and computing/Information technology 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-5880999","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":407908030,"identity":"b2eae070-b7c1-454d-8817-4640cc705f03","order_by":0,"name":"Masato Shirai","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABEElEQVRIiWNgGAWjYDACCcYGBgYDGwY2IJuZwQBJBiSBR0saSVrA5GEwyUyUu+RnN7d9+FFwXp6P/wDz54KCbfLm7A1sEgw1dgzMs7FbY3DnYPPMHoPbhm0SCWzSM4CMnT0HgFqOJTMwzjmAXYtEYjMDj8HtBKAyNmYgg3HDjfxvQPYBBsYZCdgdNiOxmfGPwbkENpDDgFrsN9x/ANT+D7cWhhuJzUDDDySwMSQwSAO1JG64wcAmwdiGW4sBSIuMQTLQL4ltIC3JG84kMFsk9iXz4PKL/Iz0x4xv/tjJy/cfPvyZ589t2w3HDzDe+PDNTs4QR4ghAeSoAzqJx3AGIR2YDpAgWcsoGAWjYBQMTwAAC9dW6MVZrbcAAAAASUVORK5CYII=","orcid":"","institution":"Shimane University","correspondingAuthor":true,"prefix":"","firstName":"Masato","middleName":"","lastName":"Shirai","suffix":""},{"id":407908031,"identity":"c34b37a6-eda5-4c96-9e32-1709fe7c771f","order_by":1,"name":"Nagayuki Okitsu","email":"","orcid":"","institution":"Shimane University","correspondingAuthor":false,"prefix":"","firstName":"Nagayuki","middleName":"","lastName":"Okitsu","suffix":""}],"badges":[],"createdAt":"2025-01-22 12:54:05","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5880999/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5880999/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":75884298,"identity":"613a288e-6a23-4682-a67a-a502e1dc9d34","added_by":"auto","created_at":"2025-02-10 08:54:04","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3883391,"visible":true,"origin":"","legend":"","description":"","filename":"tex.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5880999/v1_covered_ce6b6f75-73ae-4a64-939f-b3cd23c6e411.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"SWSformer: Sub-Window Shuffle Transformer for Image Restoration","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":"","lastPublishedDoi":"10.21203/rs.3.rs-5880999/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5880999/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Transformers have demonstrated superior performance over conventional methods in various tasks due to their ability to capture long-range dependencies and adaptively generate weights. However, their computational complexity increases quadratically with the number of tokens, limiting their applicability to high-resolution image tasks. Recent image restoration methods mitigate this by adopting mechanisms that sacrifice the ability to fully capture long-range dependencies. In contrast, Shuffle Transformer's window shuffle self-attention (WS-SA) is a mechanism that allows not only suppressing the computational complexity but also not restricting long-range dependency capture. Nevertheless, WS-SA has a problem that it causes a very sparse SA with a small receptive field for high-resolution images. In this work, we propose sub-window shuffle self-attention (SWS-SA), which is a mechanism to expand the receptive field without changing the computational complexity of WS-SA. In SWS-SA, the windows before shuffling are further partitioned into sub-windows, and shuffle is applied to them on a sub-window basis. After that, average pooling per sub-window is applied only to queries. Furthermore, we propose a Sub-Window Shuffle Transformer (SWSformer) that takes SWS-SA as its main mechanism and incorporates effective mechanisms proposed in related works. SWSformer achieves the same or better performance than state-of-the-art methods on denoising and deblurring tasks.","manuscriptTitle":"SWSformer: Sub-Window Shuffle Transformer for Image Restoration","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-01-28 04:04:26","doi":"10.21203/rs.3.rs-5880999/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":"010e0092-a8c5-4036-a33d-2721f8fc2726","owner":[],"postedDate":"January 28th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":43489611,"name":"Physical sciences/Mathematics and computing/Computer science"},{"id":43489612,"name":"Physical sciences/Mathematics and computing/Information technology"}],"tags":[],"updatedAt":"2025-02-10T08:53:24+00:00","versionOfRecord":[],"versionCreatedAt":"2025-01-28 04:04:26","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5880999","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5880999","identity":"rs-5880999","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}