Complete 3D Face Recovery: Hybrid Techniques for Occlusion and Pose- Invariant Biometric Recognition

Complete 3D Face Recovery: Hybrid Techniques for Occlusion and Pose- Invariant Biometric Recognition | 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 Complete 3D Face Recovery: Hybrid Techniques for Occlusion and Pose- Invariant Biometric Recognition M L Gangadhar, A S Raju This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7205010/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 Robust facial analysis is a critical challenge for biometric systems, particularly in the presence of pose variation and significant occlusion. This paper introduces a self-supervised framework, Complete Face Recovery GAN (CFR-GAN), which leverages 3D Morphable Models and a Swap-Rotate-and-Render (Swap-R&R) strategy to synthesise natural frontal, de-occluded facial images from single, occluded, or non-frontal inputs. The model combines a U-Net-based generator with an occlusion-aware parsing branch and a multi-scale discriminator, all trained with a composite loss that comprises adversarial, identity, perceptual, and mask terms. Empirical evaluations on CelebA-HQ, FFHQ, and Multi-PIE datasets confirm the superiority of this approach over existing methods, both in terms of recognition accuracy and qualitative restoration, eliminating the need for paired or curated training images. face recognition occlusion removal GAN 3D Morphable Model self-supervised learning face frontalization biometric restoration 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-7205010","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":490709212,"identity":"53526b39-eb47-4b4e-9cc8-d128e652f1ee","order_by":0,"name":"M L Gangadhar","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA/ElEQVRIiWNgGAWjYNACtgNAgrnxAQODBIhrAEZEaGFsBqqTkCBJSxtIOVQLHiDvfvbwix9ld+TNpx1sq/zxx6KOgb15mwRDwR2cWgzP5KVZ9px7ZjjndmLbbd42oMN4jpVJMBg8w62lIcfMgLftMOMMaaAWxgagFokcM6CWw7i19L8xM/zbdtgepKXwxx+gFvk3+LXIS+QYPwbakgjSwsDDBrKFB78WA4k3Zswy5w4nA7U0SwP9ItnGk1ZskYDPlv4c449vyg7bzpBOPvjxx586fn72wxtvfPiDx5YDDGwSKCJsICIBpwagLQ0MzB/wyI+CUTAKRsEoYGAAACB/Utvu0PMdAAAAAElFTkSuQmCC","orcid":"","institution":"Sri Siddhartha Academy of Higher Education Sri Siddhartha Institute of Technology","correspondingAuthor":true,"prefix":"","firstName":"M","middleName":"L","lastName":"Gangadhar","suffix":""},{"id":490709213,"identity":"73ba4947-9d00-43cf-a52c-fd63b2cbe7ac","order_by":1,"name":"A S Raju","email":"","orcid":"","institution":"Sri Siddhartha Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"A","middleName":"S","lastName":"Raju","suffix":""}],"badges":[],"createdAt":"2025-07-24 11:23:13","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-7205010/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7205010/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":88846265,"identity":"7e212ec9-f0f6-4720-9863-e09721fd47ca","added_by":"auto","created_at":"2025-08-12 04:07:18","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":513513,"visible":true,"origin":"","legend":"","description":"","filename":"Complete3DFaceRecoveryHybridTechniquesforOcclusionandPoseInvariantBiometricRecognition.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7205010/v1_covered_6c9094c0-25c1-4e18-a0be-25a1be1c38ea.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Complete 3D Face Recovery: Hybrid Techniques for Occlusion and Pose- Invariant Biometric Recognition","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":true,"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 recognition, occlusion removal, GAN, 3D Morphable Model, self-supervised learning, face frontalization, biometric restoration","lastPublishedDoi":"10.21203/rs.3.rs-7205010/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7205010/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Robust facial analysis is a critical challenge for biometric systems, particularly in the presence of pose variation and significant occlusion. This paper introduces a self-supervised framework, Complete Face Recovery GAN (CFR-GAN), which leverages 3D Morphable Models and a Swap-Rotate-and-Render (Swap-R\u0026R) strategy to synthesise natural frontal, de-occluded facial images from single, occluded, or non-frontal inputs. The model combines a U-Net-based generator with an occlusion-aware parsing branch and a multi-scale discriminator, all trained with a composite loss that comprises adversarial, identity, perceptual, and mask terms. Empirical evaluations on CelebA-HQ, FFHQ, and Multi-PIE datasets confirm the superiority of this approach over existing methods, both in terms of recognition accuracy and qualitative restoration, eliminating the need for paired or curated training images.","manuscriptTitle":"Complete 3D Face Recovery: Hybrid Techniques for Occlusion and Pose- Invariant Biometric Recognition","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-12 03:59:11","doi":"10.21203/rs.3.rs-7205010/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":"54ada987-feb6-4f66-8ed0-971dedd411ce","owner":[],"postedDate":"August 12th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-08-12T03:59:11+00:00","versionOfRecord":[],"versionCreatedAt":"2025-08-12 03:59:11","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7205010","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7205010","identity":"rs-7205010","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}