Enhancing Face Image Inpainting via Low-Parameter Multi-Order Feature Interaction

Enhancing Face Image Inpainting via Low-Parameter Multi-Order Feature Interaction | 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 Enhancing Face Image Inpainting via Low-Parameter Multi-Order Feature Interaction Shuang Liu, Qian Zhang, Bai Wuer, Wang Chen This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6698336/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 In computer vision, face image inpainting aims to reconstruct the lost or damaged regions, maintain visual realism. While traditional methods struggle with large missing areas or complex textures, deep learning based approaches, despite promising achievements, often come at the cost of substantial computational resources To mitigate these challenges, this paper proposes a low-parameter multi-order feature interaction method. It introduces a shadow module that utilizes low-cost linear transformations to enhance feature extraction accuracy. Additionally, a multi-order aggregation module captures and encodes middle-order features, overlooked by traditional methods, enhancing model robustness and generalization. To further reduce parameters, a fusion moment channel attention module is proposed, which optimizes feature map weighting through cross-channel fusion of multi-order statistical information. Extensive experiments on the CelebA-HQ dataset demonstrate that our method surpasses existing approaches while significantly reducing the number of parameters. our approach achieves a PSNR of 29.58 dB and an SSIM of 0.8956 for a mask ratio of (0.1, 0.6], and the parameter is 9.66 M, highlighting its effectiveness in face image inpainting tasks. face image inpainting low-parameter shadow module fusion moment channel attention multi-order aggregation 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-6698336","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":463732226,"identity":"fdb25bf7-d0f6-4f25-a2fe-9bf59269bb54","order_by":0,"name":"Shuang Liu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA00lEQVRIie3PMQrCMBTG8UghXWLnD5T0BEIkIAhFPEqL0KmCY0dBiIvgBcRLCJ1TCk49QFcpODnUC4iKk1PTTTD/+f147xFis/1g1N03eZOCU8fRZsRjelyjDKTnqtCMcMyl6Ks4OrJSGB4GEgO0kBTJvbqRGR+t28hgfcaKFZxieZoeyEJOdBsZ5grAe8syGzCio6yVYEHBRBEpJFdTEjuChXGkWEkNCSt7NXQgqavk9CAMfvG3O5LfH+D+xrlUt3TGW8lXr6e6jH9IV2Gz2Wx/0ROKXDyjLpwt9AAAAABJRU5ErkJggg==","orcid":"","institution":"Guizhou Minzu University","correspondingAuthor":true,"prefix":"","firstName":"Shuang","middleName":"","lastName":"Liu","suffix":""},{"id":463732227,"identity":"d428419c-9fbe-4d8b-997a-7bf33e2792c6","order_by":1,"name":"Qian Zhang","email":"","orcid":"","institution":"Guizhou Minzu University","correspondingAuthor":false,"prefix":"","firstName":"Qian","middleName":"","lastName":"Zhang","suffix":""},{"id":463732228,"identity":"8cb4713a-fe91-4211-b800-ce68634989b9","order_by":2,"name":"Bai Wuer","email":"","orcid":"","institution":"Guizhou Minzu University","correspondingAuthor":false,"prefix":"","firstName":"Bai","middleName":"","lastName":"Wuer","suffix":""},{"id":463732229,"identity":"dd17a08f-887f-4779-97df-8b0e8b8e11b3","order_by":3,"name":"Wang Chen","email":"","orcid":"","institution":"Guizhou Minzu University","correspondingAuthor":false,"prefix":"","firstName":"Wang","middleName":"","lastName":"Chen","suffix":""}],"badges":[],"createdAt":"2025-05-19 11:08:27","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6698336/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6698336/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":98423205,"identity":"eb1c7cff-9236-46ca-a4b5-da259aae9ecc","added_by":"auto","created_at":"2025-12-17 16:31:57","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1020274,"visible":true,"origin":"","legend":"","description":"","filename":"FaceImageInpainting.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6698336/v1_covered_bfa5df9e-c3e7-43bf-b994-d478be706c26.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Enhancing Face Image Inpainting via Low-Parameter Multi-Order Feature Interaction","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":"face image inpainting, low-parameter, shadow module, fusion moment channel attention, multi-order aggregation","lastPublishedDoi":"10.21203/rs.3.rs-6698336/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6698336/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eIn computer vision, face image inpainting aims to reconstruct the lost or damaged regions, maintain visual realism. While traditional methods struggle with large missing areas or complex textures, deep learning based approaches, despite promising achievements, often come at the cost of substantial computational resources To mitigate these challenges, this paper proposes a low-parameter multi-order feature interaction method. It introduces a shadow module that utilizes low-cost linear transformations to enhance feature extraction accuracy. Additionally, a multi-order aggregation module captures and encodes middle-order features, overlooked by traditional methods, enhancing model robustness and generalization. To further reduce parameters, a fusion moment channel attention module is proposed, which optimizes feature map weighting through cross-channel fusion of multi-order statistical information. Extensive experiments on the CelebA-HQ dataset demonstrate that our method surpasses existing approaches while significantly reducing the number of parameters. our approach achieves a PSNR of 29.58 dB and an SSIM of 0.8956 for a mask ratio of (0.1, 0.6], and the parameter is 9.66 M, highlighting its effectiveness in face image inpainting tasks.\u003c/p\u003e","manuscriptTitle":"Enhancing Face Image Inpainting via Low-Parameter Multi-Order Feature Interaction","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-06-02 08:07:02","doi":"10.21203/rs.3.rs-6698336/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":"7f0e882f-aee9-4240-a1fd-84b49c878c2f","owner":[],"postedDate":"June 2nd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-12-11T03:24:08+00:00","versionOfRecord":[],"versionCreatedAt":"2025-06-02 08:07:02","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6698336","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6698336","identity":"rs-6698336","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}