Noise-Aware Event-Based Gaussian Splatting for Robust 3D Reconstruction

Noise-Aware Event-Based Gaussian Splatting for Robust 3D 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 Article Noise-Aware Event-Based Gaussian Splatting for Robust 3D Reconstruction Jusang Jeong, Beomsu Cho, Junghyun Oh This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6619025/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 (3D) reconstruction — the digital recovery of an object’s or scene’s geometry — is fundamental to healthcare, autonomous driving, computer graphics and architecture. Although neural radiance fields (NeRF) and Gaussian splatting have advanced camera-based pipelines, these approaches remain vulnerable to motion blur, defocus and poor illumination, which degrade geometric accuracy and visual fidelity. We present a noise-aware, event-driven Gaussian-splatting framework that harnesses event cameras—sensors that asynchronously record per-pixel brightness changes with microsecond latency and a high dynamic range—to overcome these limitations. Specifically, our method (i) reconstructs high-fidelity 3D geometry solely from event streams without relying on RGB imagery, and (ii) incorporates a hot-pixel filtering technique within COLMAP to reduce sensor-induced noise; (iii) introduces a brightness-aware loss that sharpens fine details; and (iv) incorporates an optical-flow regularizer that enforces view-to-view structural consistency. By combining the blur- and low-light robustness of event sensing with the computational efficiency of Gaussian splatting, the proposed approach produces accurate, photorealistic 3D reconstructions. Physical sciences/Engineering/Electrical and electronic engineering Physical sciences/Engineering/Mechanical engineering 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-6619025","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":483562475,"identity":"6c558251-5f20-435d-8b01-5815a3058a9a","order_by":0,"name":"Jusang Jeong","email":"","orcid":"","institution":"Kwangwoon University","correspondingAuthor":false,"prefix":"","firstName":"Jusang","middleName":"","lastName":"Jeong","suffix":""},{"id":483562476,"identity":"965a1491-eb4f-4de3-9a11-7e8e8e41c146","order_by":1,"name":"Beomsu Cho","email":"","orcid":"","institution":"Kwangwoon University","correspondingAuthor":false,"prefix":"","firstName":"Beomsu","middleName":"","lastName":"Cho","suffix":""},{"id":483562477,"identity":"ff9a07b7-f534-4bde-8f45-fc5779df265e","order_by":2,"name":"Junghyun Oh","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAvElEQVRIiWNgGAWjYBACxhlg6oCcBISfQLwWY+K1MECUHkicQbQW5tk9ZtIFFXfSZ85IYPzwgyEtn7DD5pwxk55x5lnubIkEZskehhzLBoJaZuSYSfO2Hc6dJ53AIM3AUGFA2BaolnQ56QTm3yRpSZCWTmAD2pJDjJa0YmueM4cNZ85/2GbZY5BGWIvhjOSNt3kqDstLnDl8+MaPimQitDRwwBQxNjAwENbAwCDPwP6ACGWjYBSMglEwogEA3gM3t3MtYOUAAAAASUVORK5CYII=","orcid":"","institution":"Kwangwoon University","correspondingAuthor":true,"prefix":"","firstName":"Junghyun","middleName":"","lastName":"Oh","suffix":""}],"badges":[],"createdAt":"2025-05-08 09:23:38","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6619025/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6619025/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":97262638,"identity":"74a20027-c76e-42b9-9f47-5c34c020db00","added_by":"auto","created_at":"2025-12-02 14:09:04","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2418142,"visible":true,"origin":"","legend":"","description":"","filename":"JusangSR.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6619025/v1_covered_e374c732-3005-4efc-b9af-90909391af7a.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Noise-Aware Event-Based Gaussian Splatting for Robust 3D 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-6619025/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6619025/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Three-dimensional (3D) reconstruction — the digital recovery of an object’s or scene’s geometry — is fundamental to healthcare, autonomous driving, computer graphics and architecture. Although neural radiance fields (NeRF) and Gaussian splatting have advanced camera-based pipelines, these approaches remain vulnerable to motion blur, defocus and poor illumination, which degrade geometric accuracy and visual fidelity. We present a noise-aware, event-driven Gaussian-splatting framework that harnesses event cameras—sensors that asynchronously record per-pixel brightness changes with microsecond latency and a high dynamic range—to overcome these limitations. Specifically, our method (i) reconstructs high-fidelity 3D geometry solely from event streams without relying on RGB imagery, and (ii) incorporates a hot-pixel filtering technique within COLMAP to reduce sensor-induced noise; (iii) introduces a brightness-aware loss that sharpens fine details; and (iv) incorporates an optical-flow regularizer that enforces view-to-view structural consistency. By combining the blur- and low-light robustness of event sensing with the computational efficiency of Gaussian splatting, the proposed approach produces accurate, photorealistic 3D reconstructions.","manuscriptTitle":"Noise-Aware Event-Based Gaussian Splatting for Robust 3D Reconstruction","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-07-14 06:06:24","doi":"10.21203/rs.3.rs-6619025/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":"3dcec977-d554-4d0d-8dff-f56f20e8aeb0","owner":[],"postedDate":"July 14th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":51345594,"name":"Physical sciences/Engineering/Electrical and electronic engineering"},{"id":51345595,"name":"Physical sciences/Engineering/Mechanical engineering"}],"tags":[],"updatedAt":"2025-12-02T14:08:37+00:00","versionOfRecord":[],"versionCreatedAt":"2025-07-14 06:06:24","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6619025","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6619025","identity":"rs-6619025","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}