UrbanMod: Text-to-3D Modeling for Accelerated City Architecture Planning | 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Article UrbanMod: Text-to-3D Modeling for Accelerated City Architecture Planning Haoran Xu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7306090/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 Urban planning involves intricate processes traditionally reliant on visual and spatial representation. With advancements in technology, bridging text and 3D modeling can enhance these processes. We present UrbanMod, a pioneering framework designed for converting textual descriptions of urban settings into intricate 3D models. This approach utilizes cutting-edge natural language processing to accurately capture architectural features and spatial configurations from written input. By facilitating swift prototyping, UrbanMod enhances visualization capabilities for city layouts. The framework employs generative modeling techniques to deliver detailed and flexible 3D representations. Validation through various case studies underscores UrbanMod's capacity to shorten planning durations and foster better engagement among stakeholders in urban design. Smart Planning Spatial Representation Diffusion Model Full Text Additional Declarations The authors declare no competing interests. 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-7306090","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":496371538,"identity":"fbf964e3-76fd-42e4-ac52-88d8d26d76e5","order_by":0,"name":"Haoran Xu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA3ElEQVRIiWNgGAWjYBACAwbmww8SeGwYGNgZGJiBXCBIIKSFLc3gg0waSD3RWngMJGfYHIZqYSBCi7lEgoExT855eX5mHtPNBQV2DPzsOQZ4tVj2HEh4zHPmtuHMZh6z2zMMkhkke97g12JwvOGAMW/P7QSDw0AtPAZA79wgYIvBYcYGad5/52Ba6hnsCWo53swgOYPnAEzLYQYDCUJazhxjM/jAkwz0C1sZ0C/HeSTOPCvAr+VG/mdgVNrJ87M3b7td8Kdajr89eQNeLRiAhzTlo2AUjIJRMAqwAgA9rUMWh5zZXQAAAABJRU5ErkJggg==","orcid":"","institution":"Columbia University","correspondingAuthor":true,"prefix":"","firstName":"Haoran","middleName":"","lastName":"Xu","suffix":""}],"badges":[],"createdAt":"2025-08-06 06:00:29","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-7306090/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7306090/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":88498406,"identity":"20f738ca-61be-4142-af4c-a36697f2d16e","added_by":"auto","created_at":"2025-08-07 06:32:08","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":744246,"visible":true,"origin":"","legend":"","description":"","filename":"UrbanModTextto3DModelingforAcceleratedCityArchitecturePlanning2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7306090/v1_covered_2fd6316d-119b-461c-a988-43973166af86.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eUrbanMod: Text-to-3D Modeling for Accelerated City Architecture Planning\u003c/p\u003e","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":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":"Smart Planning, Spatial Representation, Diffusion Model","lastPublishedDoi":"10.21203/rs.3.rs-7306090/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7306090/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eUrban planning involves intricate processes traditionally reliant on visual and spatial representation. With advancements in technology, bridging text and 3D modeling can enhance these processes. We present UrbanMod, a pioneering framework designed for converting textual descriptions of urban settings into intricate 3D models. This approach utilizes cutting-edge natural language processing to accurately capture architectural features and spatial configurations from written input. By facilitating swift prototyping, UrbanMod enhances visualization capabilities for city layouts. The framework employs generative modeling techniques to deliver detailed and flexible 3D representations. Validation through various case studies underscores UrbanMod's capacity to shorten planning durations and foster better engagement among stakeholders in urban design.\u0026nbsp;\u003c/p\u003e","manuscriptTitle":"UrbanMod: Text-to-3D Modeling for Accelerated City Architecture Planning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-07 06:23:59","doi":"10.21203/rs.3.rs-7306090/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":"946d2eef-ce12-4446-ad72-a364a60875c8","owner":[],"postedDate":"August 7th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-08-07T06:23:59+00:00","versionOfRecord":[],"versionCreatedAt":"2025-08-07 06:23:59","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7306090","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7306090","identity":"rs-7306090","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}
Text is read by the "Ask this paper" AI Q&A widget below.
Extraction quality varies by source — PMC NXML preserves structure
cleanly, OA-HTML may include some navigation residue, and OA-PDF can
have broken hyphenation. The publisher copy
(via DOI)
is the canonical version.