Single Slice-to-3D Reconstruction in Medical Imaging and Natural Objects: A Comparative Benchmark with SAM 3D

Single Slice-to-3D Reconstruction in Medical Imaging and Natural Objects: A Comparative Benchmark with SAM 3D | 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 Single Slice-to-3D Reconstruction in Medical Imaging and Natural Objects: A Comparative Benchmark with SAM 3D Yan Luo, Advaith Ravishankar, Serena Liu, Yutong Yang, Mengyu Wang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9000089/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 While three-dimensional imaging is essential for clinical diagnosis, its high cost and long wait times have motivated the use of image-to-3D foundation models to infer volume from two-dimensional modalities. However, because these models are trained on natural images, their learned geometric priors struggle to transfer to inherently planar medical data. A benchmark of five state-of-the-art models (SAM3D, Hunyuan3D-2.1, Direct3D, Hi3DGen, and TripoSG) across six medical and two natural datasets revealed that voxel-based overlap remains uniformly low across all methods due to severe depth ambiguity from single-slice inputs. Despite this fundamental volumetric failure, global distance metrics indicate that SAM3D best captures topological similarity to ground-truth medical shapes, whereas alternative models are prone to oversimplification. Ultimately, these findings quantify the limits of zero-shot single-slice 3D inference, highlighting that reliable medical 3D reconstruction requires domain-specific adaptation and anatomical constraints to overcome complex medical geometries. Health sciences/Anatomy Biological sciences/Computational biology and bioinformatics Health sciences/Health care Physical sciences/Mathematics and computing Health sciences/Medical research 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-9000089","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":605069342,"identity":"443c45a9-2745-4ec1-a445-ae3bf04e3cb8","order_by":0,"name":"Yan Luo","email":"","orcid":"","institution":"Harvard University","correspondingAuthor":false,"prefix":"","firstName":"Yan","middleName":"","lastName":"Luo","suffix":""},{"id":605069343,"identity":"a9d183ee-f050-4247-82ef-abdd51891b2d","order_by":1,"name":"Advaith Ravishankar","email":"","orcid":"","institution":"Harvard University","correspondingAuthor":false,"prefix":"","firstName":"Advaith","middleName":"","lastName":"Ravishankar","suffix":""},{"id":605069345,"identity":"6e2b20c6-20b9-40b8-b732-79da57d851c4","order_by":2,"name":"Serena Liu","email":"","orcid":"","institution":"Harvard University","correspondingAuthor":false,"prefix":"","firstName":"Serena","middleName":"","lastName":"Liu","suffix":""},{"id":605069346,"identity":"7364c25b-6f92-4467-b82d-be29b3ecefb5","order_by":3,"name":"Yutong Yang","email":"","orcid":"","institution":"Harvard University","correspondingAuthor":false,"prefix":"","firstName":"Yutong","middleName":"","lastName":"Yang","suffix":""},{"id":605069347,"identity":"078ad56c-c2ba-47a2-be96-ba1975222d86","order_by":4,"name":"Mengyu Wang","email":"data:image/png;base64,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","orcid":"","institution":"Harvard University","correspondingAuthor":true,"prefix":"","firstName":"Mengyu","middleName":"","lastName":"Wang","suffix":""}],"badges":[],"createdAt":"2026-03-01 08:23:16","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9000089/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9000089/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108181575,"identity":"3a77982f-0e9e-489d-bc3a-2d7ce1982032","added_by":"auto","created_at":"2026-04-30 08:58:46","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3871481,"visible":true,"origin":"","legend":"","description":"","filename":"npjDMBenchmark3DReconstruction.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9000089/v1_covered_f4467282-b8e4-47ff-915a-657f8610b566.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Single Slice-to-3D Reconstruction in Medical Imaging and Natural Objects: A Comparative Benchmark with SAM 3D","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-9000089/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9000089/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"While three-dimensional imaging is essential for clinical diagnosis, its high cost and long wait times have motivated the use of image-to-3D foundation models to infer volume from two-dimensional modalities. However, because these models are trained on natural images, their learned geometric priors struggle to transfer to inherently planar medical data. A benchmark of five state-of-the-art models (SAM3D, Hunyuan3D-2.1, Direct3D, Hi3DGen, and TripoSG) across six medical and two natural datasets revealed that voxel-based overlap remains uniformly low across all methods due to severe depth ambiguity from single-slice inputs. Despite this fundamental volumetric failure, global distance metrics indicate that SAM3D best captures topological similarity to ground-truth medical shapes, whereas alternative models are prone to oversimplification. Ultimately, these findings quantify the limits of zero-shot single-slice 3D inference, highlighting that reliable medical 3D reconstruction requires domain-specific adaptation and anatomical constraints to overcome complex medical geometries.","manuscriptTitle":"Single Slice-to-3D Reconstruction in Medical Imaging and Natural Objects: A Comparative Benchmark with SAM 3D","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-13 18:42:39","doi":"10.21203/rs.3.rs-9000089/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":"7e3bbd8e-c233-4053-bd28-26f2b2b7f355","owner":[],"postedDate":"March 13th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":64392464,"name":"Health sciences/Anatomy"},{"id":64392467,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":64392468,"name":"Health sciences/Health care"},{"id":64392469,"name":"Physical sciences/Mathematics and computing"},{"id":64392470,"name":"Health sciences/Medical research"}],"tags":[],"updatedAt":"2026-04-28T16:25:12+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-13 18:42:39","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9000089","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9000089","identity":"rs-9000089","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}