Action Unit-Based 3D Face Reconstruction Using Transformers

Action Unit-Based 3D Face Reconstruction Using Transformers | 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 Action Unit-Based 3D Face Reconstruction Using Transformers Hyeonjin Kim, Pei Wang, Hyukjoon Lee This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4234443/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 The reconstruction of 3D face shapes and expressions from single 2D images remains unconquered due to the lack of detailed modeling of human facial movements such as the correlation between the different parts of faces. Facial action units (AUs), which represent detailed taxonomy of the human facial movements based on observation of activation of muscles or muscle groups, can be used to model various facial expression types. We present a novel 3D face reconstruction framework called AU feature-based 3D FAce Reconstruction using Transformer (AUFART) that can generate a 3D face model that is responsive to AU activation given a single monocular 2D image to capture expressions. AUFART leverages AU-specific features as well as facial global features to achieve accurate 3D reconstruction of facial expressions using transformers. We also introduce a loss function which is to force the learning toward the minimal discrepancy in AU activations between the input and rendered reconstruction. The proposed framework achieves an average F1 score of 0.39, outperforming state-of-the-art methods. 3D face reconstruction Facial action unit Transformer Deep learning 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-4234443","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":289077186,"identity":"65bb6746-0b73-4b0a-b329-24e5829b6e6f","order_by":0,"name":"Hyeonjin Kim","email":"","orcid":"","institution":"Kwangwoon University","correspondingAuthor":false,"prefix":"","firstName":"Hyeonjin","middleName":"","lastName":"Kim","suffix":""},{"id":289077187,"identity":"8e03ec24-b73e-4ef9-8a18-1c500ab078d6","order_by":1,"name":"Pei Wang","email":"","orcid":"","institution":"Kwangwoon University","correspondingAuthor":false,"prefix":"","firstName":"Pei","middleName":"","lastName":"Wang","suffix":""},{"id":289077188,"identity":"428c332b-3040-467b-9fb5-7fafd2dd2bb2","order_by":2,"name":"Hyukjoon Lee","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAoklEQVRIiWNgGAWjYBACA3Yg8eEAmM1MpBagOsYZJGth5iFJizkz88HHNmcOM/C3H2A2riBGi2UzW7Jxzo3DDBJnEpgTzxDlsMM8ZtI5H24zMNxgYD7YQJwW/u+/LYBa5EnQwsPGzHDjNoMBUEsikVrYjCV7zvznMTyT2GxInJbjzQ8//DiWJid3/PBhSaK0wAAPMEZJ0jAKRsEoGAWjAB8AAIOjMNarXirqAAAAAElFTkSuQmCC","orcid":"","institution":"Kwangwoon University","correspondingAuthor":true,"prefix":"","firstName":"Hyukjoon","middleName":"","lastName":"Lee","suffix":""}],"badges":[],"createdAt":"2024-04-08 06:45:54","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4234443/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4234443/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":54604596,"identity":"e55fa3cd-8f70-4c2e-9565-d9dac78fd58f","added_by":"auto","created_at":"2024-04-13 01:59:35","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":806157,"visible":true,"origin":"","legend":"","description":"","filename":"springer0408hlee.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4234443/v1_covered_283b1d07-2997-4a05-a2c9-3b964030fb21.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Action Unit-Based 3D Face Reconstruction Using Transformers","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":"3D face reconstruction, Facial action unit, Transformer, Deep learning","lastPublishedDoi":"10.21203/rs.3.rs-4234443/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4234443/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe reconstruction of 3D face shapes and expressions from single 2D images remains unconquered due to the lack of detailed modeling of human facial movements such as the correlation between the different parts of faces. Facial action units (AUs), which represent detailed taxonomy of the human facial movements based on observation of activation of muscles or muscle groups, can be used to model various facial expression types. We present a novel 3D face reconstruction framework called AU feature-based 3D FAce Reconstruction using Transformer (AUFART) that can generate a 3D face model that is responsive to AU activation given a single monocular 2D image to capture expressions. AUFART leverages AU-specific features as well as facial global features to achieve accurate 3D reconstruction of facial expressions using transformers. We also introduce a loss function which is to force the learning toward the minimal discrepancy in AU activations between the input and rendered reconstruction. The proposed framework achieves an average F1 score of 0.39, outperforming state-of-the-art methods.\u003c/p\u003e","manuscriptTitle":"Action Unit-Based 3D Face Reconstruction Using Transformers","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-04-12 18:26:42","doi":"10.21203/rs.3.rs-4234443/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":"1f73af63-8721-409b-9f0f-5e38fbe6b131","owner":[],"postedDate":"April 12th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-04-23T15:03:16+00:00","versionOfRecord":[],"versionCreatedAt":"2024-04-12 18:26:42","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4234443","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4234443","identity":"rs-4234443","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}