Adaptive Diffusion Refinement for Enhanced 3D Surface Reconstruction under Geometric Complexity

Adaptive Diffusion Refinement for Enhanced 3D Surface Reconstruction under Geometric Complexity | 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 Adaptive Diffusion Refinement for Enhanced 3D Surface Reconstruction under Geometric Complexity Fei Chen, Ying He, Xiantao Chen, Gong He, Bingcai Chen This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7669529/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 Three-dimensional point cloud reconstruction aims to recover continuous, geometrically consistent surfaces from sparse, unstructured samples, playing a pivotal role in 3D perception and modeling systems. Traditional methods often struggle with spatial nonuniformity and abrupt geometric changes, leading to over-smoothing or artifacts. To address these challenges, we introduce a Geometry-Complexity-Aware Diffusion (GCAD) framework that employs diffusion as a region-adaptive feature refiner. This framework utilizes regional complexity scores to drive adaptive timestep allocation and integrates multi-scale features via a confidence-aware fusion module, improving stability and consistency under sparse and noisy inputs. Experiments on ShapeNet, SyntheticRoom, and ScanNet demonstrate consistent improvements over strong baselines, with GCAD achieving a 15\% reduction in Chamfer Distance and a 10\% increase in F-score on ShapeNet. The adaptive scheduling mechanism also ensures a better balance between quality and computational efficiency. Our findings substantiate the effectiveness of geometry-complexity-aware adaptive refinement in enhancing reconstruction accuracy and geometric consistency.Our source code are available at https://github.com/kamiya1001hana/GCAD.git Artificial Intelligence and Machine Learning 3D point cloud reconstruction geometry-complexity-aware diffusion structural complexity modeling neural implicit surface kernel field representation 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-7669529","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":518488661,"identity":"15d8de46-8150-4bca-819d-ca1a9d1412d5","order_by":0,"name":"Fei Chen","email":"","orcid":"","institution":"Chongqing University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Fei","middleName":"","lastName":"Chen","suffix":""},{"id":518488662,"identity":"0bc1295c-df01-418f-9954-5f430323ccff","order_by":1,"name":"Ying He","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAArUlEQVRIiWNgGAWjYBACA4aExAdwNrFakkFKJUjSwiZBmhZz9oRnFT/KDtcxsDdvk2CouUNYi2XPg7SbPecOSzDwHCuTYDj2jAiH3UhIu83YBtQikWMmwdhwmDgtxWAt8m9I0MIMsYWHWC1nHiRL9pxLl2zjSSu2SDhGjJbjOYkffpRZ8/OzH95440MNEVoYGHgSGBjYwIiBIYEYDQwM7Aeg6kfBKBgFo2AU4AAAoQQ3jREUuncAAAAASUVORK5CYII=","orcid":"","institution":"Chongqing University of Technology","correspondingAuthor":true,"prefix":"","firstName":"Ying","middleName":"","lastName":"He","suffix":""},{"id":518488663,"identity":"874b52b1-fa44-4dad-9670-bd08d82f035c","order_by":2,"name":"Xiantao Chen","email":"","orcid":"","institution":"China Construction Technology Group Western Co., Ltd","correspondingAuthor":false,"prefix":"","firstName":"Xiantao","middleName":"","lastName":"Chen","suffix":""},{"id":518488664,"identity":"a38070c9-2a56-400b-ba59-62a636e8f0fe","order_by":3,"name":"Gong He","email":"","orcid":"","institution":"State Grid Chongqing Electric Power Company","correspondingAuthor":false,"prefix":"","firstName":"Gong","middleName":"","lastName":"He","suffix":""},{"id":518488665,"identity":"a78b334c-2382-4736-aef6-a7979450b292","order_by":4,"name":"Bingcai Chen","email":"","orcid":"","institution":"Chongqing University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Bingcai","middleName":"","lastName":"Chen","suffix":""}],"badges":[],"createdAt":"2025-09-22 06:17:10","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-7669529/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7669529/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":92077805,"identity":"2378a747-d6d1-4c75-aaa4-b586ad7e2993","added_by":"auto","created_at":"2025-09-24 11:09:21","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":5626837,"visible":true,"origin":"","legend":"","description":"","filename":"TheVisualComputer.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7669529/v1_covered_4c0ee2ed-ccee-4988-9d5b-39194868c07e.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eAdaptive Diffusion Refinement for Enhanced 3D Surface Reconstruction under Geometric Complexity\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":"3D point cloud reconstruction, geometry-complexity-aware diffusion, structural complexity modeling, neural implicit surface, kernel field representation","lastPublishedDoi":"10.21203/rs.3.rs-7669529/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7669529/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThree-dimensional point cloud reconstruction aims to recover continuous, geometrically consistent surfaces from sparse, unstructured samples, playing a pivotal role in 3D perception and modeling systems. Traditional methods often struggle with spatial nonuniformity and abrupt geometric changes, leading to over-smoothing or artifacts. To address these challenges, we introduce a Geometry-Complexity-Aware Diffusion (GCAD) framework that employs diffusion as a region-adaptive feature refiner. This framework utilizes regional complexity scores to drive adaptive timestep allocation and integrates multi-scale features via a confidence-aware fusion module, improving stability and consistency under sparse and noisy inputs. Experiments on ShapeNet, SyntheticRoom, and ScanNet demonstrate consistent improvements over strong baselines, with GCAD achieving a 15\\% reduction in Chamfer Distance and a 10\\% increase in F-score on ShapeNet. The adaptive scheduling mechanism also ensures a better balance between quality and computational efficiency. Our findings substantiate the effectiveness of geometry-complexity-aware adaptive refinement in enhancing reconstruction accuracy and geometric consistency.Our source code are available at https://github.com/kamiya1001hana/GCAD.git\u003c/p\u003e","manuscriptTitle":"Adaptive Diffusion Refinement for Enhanced 3D Surface Reconstruction under Geometric Complexity","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-24 11:01:09","doi":"10.21203/rs.3.rs-7669529/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":"bd6b54ad-2c25-49eb-bff1-5c393cac2887","owner":[],"postedDate":"September 24th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":55090120,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2025-09-24T11:01:09+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-24 11:01:09","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7669529","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7669529","identity":"rs-7669529","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}