Evaluation of One-image 3D Reconstruction for Plant Model Generation

Evaluation of One-image 3D Reconstruction for Plant Model Generation | 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 Evaluation of One-image 3D Reconstruction for Plant Model Generation Zihe Gao, Zane Hartley, Andrew French This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7577309/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 13 Jan, 2026 Read the published version in Plant Methods → Version 1 posted 11 You are reading this latest preprint version Abstract Generating accurate and visually realistic 3D models of plants from single-view images is crucial yet remains challenging due to plants' intricate geometry and frequent occlusions. This capability matters because it supplements current plant datasets and enables non-destructive, high-throughput phenotyping for crop breeding and precision agriculture. More broadly, 3D reconstruction is particularly important because plant morphology is inherently three-dimensional, while 2D representations miss occluded leaves, branching geometry, and volumetric traits. However, plants present unique challenges compared to common rigid objects, and most current generative methods have not been systematically tested in this domain, leaving a gap in understanding their reliability for realistic plant reconstruction. This study systematically evaluates six advanced generative techniques—Hunyuan3D 2.0, Trellis (Structured 3D Latents), One2345++, InstantMesh, Direct3D and Unique3D—using the existing PlantDreamer dataset. Specifically, this research reconstructs mesh models from images of Bean plants and quantitatively assesses each method’s performance against ground-truth scans using Chamfer Distance, Normal Consistency, F-Score, PSNR, LPIPS, and CLIP Score. The paper also presents qualitative results of Kale and Mint plants. The results indicate that Hunyuan3D 2.0 achieves superior performance overall, suggesting its effectiveness in capturing complex plant structures. This work provides valuable insights into strengths and limitations of contemporary 3D generative approaches, guiding future improvements in realistic plant digitisation. 3D plant reconstruction image-conditioned generation diffusion models plant digitisation PlantDreamer dataset single-image reconstruction Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 13 Jan, 2026 Read the published version in Plant Methods → Version 1 posted Editorial decision: Revision requested 14 Nov, 2025 Reviews received at journal 13 Nov, 2025 Reviewers agreed at journal 03 Nov, 2025 Reviewers agreed at journal 01 Oct, 2025 Reviews received at journal 01 Oct, 2025 Reviewers agreed at journal 29 Sep, 2025 Reviewers agreed at journal 28 Sep, 2025 Reviewers invited by journal 22 Sep, 2025 Editor assigned by journal 12 Sep, 2025 Submission checks completed at journal 12 Sep, 2025 First submitted to journal 09 Sep, 2025 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-7577309","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":523925013,"identity":"87c947de-6e3a-411a-9b27-14253c930544","order_by":0,"name":"Zihe Gao","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABDklEQVRIiWNgGAWjYHACNjDJDyYNwAgCJAhpkWxgYGw4QJIWgwMgLQxEaJFvP/zsAcMvOznj283HH38ouGO3nf10AsOPGobEmQ3YtTD2pJkbMPYlG5vdOZYIdNiz5J09uRsYe44xJM7GYQszQw6bBGMPc+K2GzmGQC2Hkw0O5G5g4G1gSJyHyyP8b0Ba6hM3z4BpOf92A+NfPFp4JIC2MPw4nLhBAqLFzuBG7gZmkC24HCYh8cxMIrHhuLHEjbTEGWcMDicY3Hi74bDMMQljXN6X709+JvHhT7Uc/4zkAx8q/hy2Nzifu/Hhmxob2RkHcFgDAoltSGyQ2QfwRiQY/EEw7QkoHQWjYBSMghEIAHGXYfXjTp/SAAAAAElFTkSuQmCC","orcid":"","institution":"University of Nottingham","correspondingAuthor":true,"prefix":"","firstName":"Zihe","middleName":"","lastName":"Gao","suffix":""},{"id":523925014,"identity":"fd834021-5ac9-43c5-ad56-18aa56c9ce7e","order_by":1,"name":"Zane Hartley","email":"","orcid":"","institution":"University of Nottingham","correspondingAuthor":false,"prefix":"","firstName":"Zane","middleName":"","lastName":"Hartley","suffix":""},{"id":523925015,"identity":"accd3a45-731e-4e4c-bef7-b2f06140b645","order_by":2,"name":"Andrew French","email":"","orcid":"","institution":"University of Nottingham","correspondingAuthor":false,"prefix":"","firstName":"Andrew","middleName":"","lastName":"French","suffix":""}],"badges":[],"createdAt":"2025-09-09 22:53:03","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7577309/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7577309/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1186/s13007-025-01482-6","type":"published","date":"2026-01-13T16:29:46+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":92856189,"identity":"04069aa8-7a8c-4d9b-aa1e-0cb238f34eb2","added_by":"auto","created_at":"2025-10-06 11:31:15","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5373,"visible":true,"origin":"","legend":"","description":"","filename":"d354a31321854538be1cc17c2108f9d1.json","url":"https://assets-eu.researchsquare.com/files/rs-7577309/v1/a3892a406b1fe004434c35c5.json"},{"id":100614604,"identity":"ba1f542f-96dc-4df1-81fb-bc58aef86e0f","added_by":"auto","created_at":"2026-01-19 17:22:15","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":5015128,"visible":true,"origin":"","legend":"","description":"","filename":"EvaluationofOneimage3DReconstructionforPlantModelGeneration.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7577309/v1_covered_90b202ce-c6db-4c43-ae73-c4624f533410.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Evaluation of One-image 3D Reconstruction for Plant Model Generation","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"plant-methods","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"plme","sideBox":"Learn more about [Plant Methods](http://plantmethods.biomedcentral.com/)","snPcode":"13007","submissionUrl":"https://submission.nature.com/new-submission/13007/3","title":"Plant Methods","twitterHandle":"@PlantMethods","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"3D plant reconstruction, image-conditioned generation, diffusion models, plant digitisation, PlantDreamer dataset, single-image reconstruction","lastPublishedDoi":"10.21203/rs.3.rs-7577309/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7577309/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Generating accurate and visually realistic 3D models of plants from single-view images is crucial yet remains challenging due to plants' intricate geometry and frequent occlusions. This capability matters because it supplements current plant datasets and enables non-destructive, high-throughput phenotyping for crop breeding and precision agriculture. More broadly, 3D reconstruction is particularly important because plant morphology is inherently three-dimensional, while 2D representations miss occluded leaves, branching geometry, and volumetric traits. However, plants present unique challenges compared to common rigid objects, and most current generative methods have not been systematically tested in this domain, leaving a gap in understanding their reliability for realistic plant reconstruction.\nThis study systematically evaluates six advanced generative techniques—Hunyuan3D 2.0, Trellis (Structured 3D Latents), One2345++, InstantMesh, Direct3D and Unique3D—using the existing PlantDreamer dataset. Specifically, this research reconstructs mesh models from images of Bean plants and quantitatively assesses each method’s performance against ground-truth scans using Chamfer Distance, Normal Consistency, F-Score, PSNR, LPIPS, and CLIP Score. The paper also presents qualitative results of Kale and Mint plants. The results indicate that Hunyuan3D 2.0 achieves superior performance overall, suggesting its effectiveness in capturing complex plant structures. This work provides valuable insights into strengths and limitations of contemporary 3D generative approaches, guiding future improvements in realistic plant digitisation.","manuscriptTitle":"Evaluation of One-image 3D Reconstruction for Plant Model Generation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-06 11:31:11","doi":"10.21203/rs.3.rs-7577309/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-11-14T16:56:40+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-11-13T16:26:40+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"335174842460493836413255920805491919311","date":"2025-11-03T16:30:39+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"296834028790121940371212863253140554454","date":"2025-10-01T12:53:29+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-01T11:55:26+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"310639489422644233809267153308942860635","date":"2025-09-29T06:22:16+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"152973463027364388054272558723995373289","date":"2025-09-29T01:04:27+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-09-22T17:50:30+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-09-12T06:20:25+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-09-12T06:18:59+00:00","index":"","fulltext":""},{"type":"submitted","content":"Plant Methods","date":"2025-09-09T22:38:43+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"plant-methods","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"plme","sideBox":"Learn more about [Plant Methods](http://plantmethods.biomedcentral.com/)","snPcode":"13007","submissionUrl":"https://submission.nature.com/new-submission/13007/3","title":"Plant Methods","twitterHandle":"@PlantMethods","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"b006abd6-1d17-4a87-8b9d-8713a7ffa46c","owner":[],"postedDate":"October 6th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2026-01-19T16:47:04+00:00","versionOfRecord":{"articleIdentity":"rs-7577309","link":"https://doi.org/10.1186/s13007-025-01482-6","journal":{"identity":"plant-methods","isVorOnly":false,"title":"Plant Methods"},"publishedOn":"2026-01-13 16:29:46","publishedOnDateReadable":"January 13th, 2026"},"versionCreatedAt":"2025-10-06 11:31:11","video":"","vorDoi":"10.1186/s13007-025-01482-6","vorDoiUrl":"https://doi.org/10.1186/s13007-025-01482-6","workflowStages":[]},"version":"v1","identity":"rs-7577309","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7577309","identity":"rs-7577309","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}