Global Soft Pooling Adaptive Attention Network for Single Aerial Image-Based 3D Outdoor Scene Reconstruction

Global Soft Pooling Adaptive Attention Network for Single Aerial Image-Based 3D Outdoor Scene Reconstruction | 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 Global Soft Pooling Adaptive Attention Network for Single Aerial Image-Based 3D Outdoor Scene Reconstruction Wenju Wang, Wei Li, Ruipeng Yan This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3507344/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 In the realm of outdoor scene 3D reconstruction from a solitary RGB aerial image, a persistent challenge pertains to the issue of inadequate reconstruction accuracy. In this article, we introduce a novel approach, namely, the Global Soft Pooling Adaptive Attention Network, designed to facilitate high-precision 3D scene reconstruction in outdoor environments. This network primarily comprises two distinct attention network modules: the Global Soft Pooling Dynamic Convolutional Attention and the Three-Head Adaptive Graph Attention. The Global Soft Pooling Attention Network employs a stem_conv and four MBdyconv components for the extraction of multi-scale image features. It harnesses global soft pooling techniques, integrating both channels fusion and spatial attention mechanisms, thereby enabling the precise acquisition of composite features. These features are subsequently assigned to initialize mesh vertices. The Three-Head Adaptive Graph Attention Network leverages three sets of adaptive 1D convolutions to derive 3D vertex features, taking into account the weights of neighboring vertices. A linear layer is employed to compute the vertex coordinate offsets (denoted as " ΔV "), which are then utilized to refine the initial mesh vertices, ultimately achieving an enhanced mesh model. When evaluated on the publicly available SensatUrban dataset, our proposed method demonstrates impressive performance metrics, achieving a reconstruction performance index of 0.96 for l 2 and 1.68 for l 3 . Experimental results unequivocally demonstrate that our approach outperforms existing deep learning methodologies, establishing itself as the state-of-the-art solution for outdoor 3D scene reconstruction. 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-3507344","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":244139719,"identity":"5674cb4e-615e-4670-ab1e-a04513c18530","order_by":0,"name":"Wenju Wang","email":"","orcid":"","institution":"University of Shanghai for Science and Technology","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Wenju","middleName":"","lastName":"Wang","suffix":""},{"id":244139720,"identity":"3345b8c1-947a-4885-821c-749e44df39b1","order_by":1,"name":"Wei Li","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABDUlEQVRIie3QMWrDMBSA4ScE8vIgq4zBZ1AQlJaEeOhFZAzuYroUSroEQyBZfAAXehgVDV5Csxq62FOWDpk6lVI5S8kgN2MH/YMGoQ9JD8Dn+4dNaGA6vpzHSVP+7vIxEm4xF9e7XMJOkxPCv4jYg+BPG5OWrbqQgAElWmYkeT4cOrJZJQnQ13eExb1LkDXRfY13MY2KaUnsdRWwbIaQPbgIpaAk5zPJooJYohUCXkUIOi0dhFEQ0ZegaRU2fTk8DGHyOUrQEs7VbVpzGB5GSQXIRgmndshc51JgMa3Vm/2LYfLmRWROkuwb04Xf81gETXc8Pq6SYLvu24/lwknOU6eJDIu46LzP5/P5HP0A0dpPvf6YcOAAAAAASUVORK5CYII=","orcid":"","institution":"University of Shanghai for Science and Technology","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Wei","middleName":"","lastName":"Li","suffix":""},{"id":244139721,"identity":"d16811d4-8f16-4f56-b86b-78b67f2db92e","order_by":2,"name":"Ruipeng Yan","email":"","orcid":"","institution":"University of Shanghai for Science and Technology","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Ruipeng","middleName":"","lastName":"Yan","suffix":""}],"badges":[],"createdAt":"2023-10-29 13:14:12","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3507344/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3507344/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":72343314,"identity":"8cbc599e-69ce-43d0-941e-c6f258e21e4c","added_by":"auto","created_at":"2024-12-25 21:31:20","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":982715,"visible":true,"origin":"","legend":"","description":"","filename":"GlobalSoftPoolingAdaptiveAttentionNetworkforSingleAerialImageBased3DOutdoorSceneReconstruction.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3507344/v1_covered_78dea806-fc33-42e4-8425-7742337f2df9.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Global Soft Pooling Adaptive Attention Network for Single Aerial Image-Based 3D Outdoor Scene Reconstruction","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-3507344/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3507344/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eIn the realm of outdoor scene 3D reconstruction from a solitary RGB aerial image, a persistent challenge pertains to the issue of inadequate reconstruction accuracy. In this article, we introduce a novel approach, namely, the Global Soft Pooling Adaptive Attention Network, designed to facilitate high-precision 3D scene reconstruction in outdoor environments. This network primarily comprises two distinct attention network modules: the Global Soft Pooling Dynamic Convolutional Attention and the Three-Head Adaptive Graph Attention. The Global Soft Pooling Attention Network employs a stem_conv and four MBdyconv components for the extraction of multi-scale image features. It harnesses global soft pooling techniques, integrating both channels fusion and spatial attention mechanisms, thereby enabling the precise acquisition of composite features. These features are subsequently assigned to initialize mesh vertices. The Three-Head Adaptive Graph Attention Network leverages three sets of adaptive 1D convolutions to derive 3D vertex features, taking into account the weights of neighboring vertices. A linear layer is employed to compute the vertex coordinate offsets (denoted as \"\u003cem\u003eΔV\u003c/em\u003e\"), which are then utilized to refine the initial mesh vertices, ultimately achieving an enhanced mesh model. When evaluated on the publicly available SensatUrban dataset, our proposed method demonstrates impressive performance metrics, achieving a reconstruction performance index of 0.96 for \u003cem\u003el\u003c/em\u003e\u003csub\u003e\u003cem\u003e2\u003c/em\u003e\u003c/sub\u003e and 1.68 for \u003cem\u003el\u003c/em\u003e\u003csub\u003e\u003cem\u003e3\u003c/em\u003e\u003c/sub\u003e. Experimental results unequivocally demonstrate that our approach outperforms existing deep learning methodologies, establishing itself as the state-of-the-art solution for outdoor 3D scene reconstruction.\u003c/p\u003e","manuscriptTitle":"Global Soft Pooling Adaptive Attention Network for Single Aerial Image-Based 3D Outdoor Scene Reconstruction","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2023-11-01 07:18:22","doi":"10.21203/rs.3.rs-3507344/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":"4864040f-ff9c-4442-ab9c-703d2b354e69","owner":[],"postedDate":"November 1st, 2023","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-12-25T21:23:12+00:00","versionOfRecord":[],"versionCreatedAt":"2023-11-01 07:18:22","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-3507344","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3507344","identity":"rs-3507344","version":["v1"]},"buildId":"ApUGefWb6u5IBVtyqm6d5","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}