3D Human Mesh Recovery with Learned Gradient

3D Human Mesh Recovery with Learned Gradient | 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PDF Research Article 3D Human Mesh Recovery with Learned Gradient Yuanyuan Song, Hui Zhou This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4603978/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 3D human body reconstruction is a research hotspot in computer vision. In this article, we propose a method for 3D human mesh recovery with learned gradient. We use gradient descent networks to predict model parameter updates. Previous studies have focused on 3D pose estimation, often ignoring the importance of body shape reconstruction. In order to improve the accuracy of human body model shape estimation, we introduce silhouette information that can represent human body shape, using silhouette and 2D joints as inputs to the neural network. In addition, throughout the entire training process, we only need the SMPL parameterized human pose dataset, without any image to 3D correspondence. The network learns effective pose and shape subspaces from this data, and performs optimization more effectively in that subspace. It has been proven that our method can achieve advanced performance on public datasets. Even on challenging datasets in the wild, competitive results can be obtained. 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-4603978","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":319753915,"identity":"9392a6e7-7c49-4290-8a81-a9eaab7e8d9e","order_by":0,"name":"Yuanyuan Song","email":"data:image/png;base64,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","orcid":"","institution":"Dalian Neusoft University of Information","correspondingAuthor":true,"prefix":"","firstName":"Yuanyuan","middleName":"","lastName":"Song","suffix":""},{"id":319753916,"identity":"4e2381a6-8665-49d0-93ce-d3e698b134b8","order_by":1,"name":"Hui Zhou","email":"","orcid":"","institution":"Dalian Neusoft University of Information","correspondingAuthor":false,"prefix":"","firstName":"Hui","middleName":"","lastName":"Zhou","suffix":""}],"badges":[],"createdAt":"2024-06-19 07:27:54","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4603978/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4603978/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":60945610,"identity":"d9c8255d-6de4-4a6e-b682-3053f4235788","added_by":"auto","created_at":"2024-07-23 22:31:35","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":515096,"visible":true,"origin":"","legend":"","description":"","filename":"3DHumanMeshRecoverywithLearnedGradient.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4603978/v1_covered_6615d468-c607-4133-baf4-3f18bdc5dffb.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"3D Human Mesh Recovery with Learned Gradient","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-4603978/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4603978/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e3D human body reconstruction is a research hotspot in computer vision. In this article, we propose a method for 3D human mesh recovery with learned gradient. We use gradient descent networks to predict model parameter updates. Previous studies have focused on 3D pose estimation, often ignoring the importance of body shape reconstruction. In order to improve the accuracy of human body model shape estimation, we introduce silhouette information that can represent human body shape, using silhouette and 2D joints as inputs to the neural network. In addition, throughout the entire training process, we only need the SMPL parameterized human pose dataset, without any image to 3D correspondence. The network learns effective pose and shape subspaces from this data, and performs optimization more effectively in that subspace. It has been proven that our method can achieve advanced performance on public datasets. Even on challenging datasets in the wild, competitive results can be obtained.\u003c/p\u003e","manuscriptTitle":"3D Human Mesh Recovery with Learned Gradient","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-07-05 03:09:45","doi":"10.21203/rs.3.rs-4603978/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":"0f94e53d-e7d6-4ccc-b83f-7d9ddefd0358","owner":[],"postedDate":"July 5th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-07-23T22:23:29+00:00","versionOfRecord":[],"versionCreatedAt":"2024-07-05 03:09:45","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4603978","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4603978","identity":"rs-4603978","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}