MiniGS: Efficient 3D Gaussian Splatting With Full Factors Weighted Pruning For Scene Representation

MiniGS: Efficient 3D Gaussian Splatting With Full Factors Weighted Pruning For Scene Representation | 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 MiniGS: Efficient 3D Gaussian Splatting With Full Factors Weighted Pruning For Scene Representation Qing Yang, Xiaonuo Dongye, Hanzhi Guo, Dongdong Weng, Le Luo This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6897837/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 08 Jan, 2026 Read the published version in Multimedia Systems → Version 1 posted 11 You are reading this latest preprint version Abstract 3D Gaussian Splatting has recently emerged as a novel 3D representation method, gaining recognition for its exceptional rendering speed and visual fidelity. However, these advancements come at a cost: this technique exhibits substantial memory demands, with optimized models often containing millions of Gaussian primitives that can exceed 1 GB of storage. We attribute this inefficiency to inherent redundancy in primitive allocation, where overlapping or non-essential elements remain unoptimized in current implementations. In this paper, we propose a novel memory-efficient Gaussian compression method named MiniGS, featuring Full Factors Weighted (FFW) Importance Score Pruning and Variational Densify Threshold (VDT) components. On one hand, we construct several importance score to selectively combine pixel coordinates, Gaussian distances and opacity on the set of Gaussian primitives, and utilize them to prune out redundancy while preserving a small number of highly contributive primitives, achieving an impressive 90% compression ratio. On the other hand, to compensate for the quality loss of pruning Gaussians, we utilize the plug-and-play Variational Densify Threshold (VDT) Component to recover fine details of the 3D scenes, effectively compensating for quality losses with primitives at a low scale. We demonstrate the performance of MiniGS with extensive experimental results on classic dataset and our self-constructed synthetic dataset. For example, our proposed method MiniGS can achieve 29.63 PSNR with 303.271 thousand Gaussian primitives, while the vanilla Gaussian splatting algorithm achieves same-level PSNR (29.73) with one order of magnitude higher of Gaussian primitives on the DeepBlending dataset. Gaussian Splatting Pointcloud Pruning Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 08 Jan, 2026 Read the published version in Multimedia Systems → Version 1 posted Editorial decision: Revision requested 30 Jul, 2025 Reviews received at journal 30 Jul, 2025 Reviews received at journal 19 Jul, 2025 Reviewers agreed at journal 11 Jul, 2025 Reviewers agreed at journal 07 Jul, 2025 Reviewers agreed at journal 07 Jul, 2025 Reviewers agreed at journal 26 Jun, 2025 Reviewers invited by journal 23 Jun, 2025 Editor assigned by journal 19 Jun, 2025 Submission checks completed at journal 19 Jun, 2025 First submitted to journal 15 Jun, 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-6897837","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":475464489,"identity":"db2e352a-fb65-4ec5-af50-d340d87e4f34","order_by":0,"name":"Qing Yang","email":"","orcid":"","institution":"Beijing Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Qing","middleName":"","lastName":"Yang","suffix":""},{"id":475464490,"identity":"adce62bb-b410-4fc1-8707-798c0c54b54d","order_by":1,"name":"Xiaonuo Dongye","email":"","orcid":"","institution":"Beijing Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Xiaonuo","middleName":"","lastName":"Dongye","suffix":""},{"id":475464491,"identity":"de26cb84-b435-46f0-8119-11f565219806","order_by":2,"name":"Hanzhi Guo","email":"","orcid":"","institution":"Beijing Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Hanzhi","middleName":"","lastName":"Guo","suffix":""},{"id":475464492,"identity":"5e4565f2-377f-4ca5-912d-a564a8959a25","order_by":3,"name":"Dongdong Weng","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAs0lEQVRIiWNgGAWjYJACg48NEmCaeC2GMxskJEjTwszbwECCFv7Zxy8U2+6wqGNgb94mwVBzh7AWiXM5Bca5Z4AO4zlWJsFw7BlhLQY8PAnGuW1ALRI5ZhKMDYeJ1GIJ0iL/hmgt7AeMGcG28BCpReIMD4Nh7xkJyTaetGKLhGNEaOHvYX9m8HNHHT8/++GNNz7UEKGFgYHHDBwfbCAigRgNDAzsjx8Qp3AUjIJRMApGLAAAQZQvY2PPbCkAAAAASUVORK5CYII=","orcid":"","institution":"Beijing Institute of Technology","correspondingAuthor":true,"prefix":"","firstName":"Dongdong","middleName":"","lastName":"Weng","suffix":""},{"id":475464493,"identity":"f2c29617-e10a-4db1-b57d-4fcf0bb4c5da","order_by":4,"name":"Le Luo","email":"","orcid":"","institution":"Pengcheng Laboratory","correspondingAuthor":false,"prefix":"","firstName":"Le","middleName":"","lastName":"Luo","suffix":""}],"badges":[],"createdAt":"2025-06-15 10:38:17","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6897837/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6897837/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s00530-025-02104-w","type":"published","date":"2026-01-08T15:58:58+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":100070003,"identity":"9cea1f54-7679-4d67-9b43-de43ef2d4a50","added_by":"auto","created_at":"2026-01-12 16:15:50","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":4741768,"visible":true,"origin":"","legend":"","description":"","filename":"AppliedIntelligencerevised0619.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6897837/v1_covered_e962906a-a314-467c-a7fe-aac01f5ae8bd.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"MiniGS: Efficient 3D Gaussian Splatting With Full Factors Weighted Pruning For Scene Representation","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":"multimedia-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mmsj","sideBox":"Learn more about [Multimedia Systems](http://link.springer.com/journal/530)","snPcode":"530","submissionUrl":"https://submission.nature.com/new-submission/530/3","title":"Multimedia Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Gaussian Splatting, Pointcloud, Pruning","lastPublishedDoi":"10.21203/rs.3.rs-6897837/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6897837/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e3D Gaussian Splatting has recently emerged as a novel 3D representation method, gaining recognition for its exceptional rendering speed and visual fidelity. However, these advancements come at a cost: this technique exhibits substantial memory demands, with optimized models often containing millions of Gaussian primitives that can exceed 1 GB of storage. We attribute this inefficiency to inherent redundancy in primitive allocation, where overlapping or non-essential elements remain unoptimized in current implementations. In this paper, we propose a novel memory-efficient Gaussian compression method named MiniGS, featuring Full Factors Weighted (FFW) Importance Score Pruning and Variational Densify Threshold (VDT) components. On one hand, we construct several importance score to selectively combine pixel coordinates, Gaussian distances and opacity on the set of Gaussian primitives, and utilize them to prune out redundancy while preserving a small number of highly contributive primitives, achieving an impressive 90% compression ratio. On the other hand, to compensate for the quality loss of pruning Gaussians, we utilize the plug-and-play Variational Densify Threshold (VDT) Component to recover fine details of the 3D scenes, effectively compensating for quality losses with primitives at a low scale. We demonstrate the performance of MiniGS with extensive experimental results on classic dataset and our self-constructed synthetic dataset. For example, our proposed method MiniGS can achieve 29.63 PSNR with 303.271 thousand Gaussian primitives, while the vanilla Gaussian splatting algorithm achieves same-level PSNR (29.73) with one order of magnitude higher of Gaussian primitives on the DeepBlending dataset.\u003c/p\u003e","manuscriptTitle":"MiniGS: Efficient 3D Gaussian Splatting With Full Factors Weighted Pruning For Scene Representation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-06-25 06:24:01","doi":"10.21203/rs.3.rs-6897837/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-07-30T07:15:22+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-07-30T04:53:46+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-07-19T08:29:32+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"109447423522716291471498390465910650444","date":"2025-07-11T12:44:10+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"255828063759636631972950812239117244453","date":"2025-07-07T09:13:04+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"296052207322376995391275542454446101831","date":"2025-07-07T05:49:51+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"174891932337332239922450876779578078875","date":"2025-06-26T11:23:32+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-06-24T02:19:11+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-06-19T15:23:36+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-06-19T11:52:03+00:00","index":"","fulltext":""},{"type":"submitted","content":"Multimedia Systems","date":"2025-06-15T10:33:56+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"multimedia-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mmsj","sideBox":"Learn more about [Multimedia Systems](http://link.springer.com/journal/530)","snPcode":"530","submissionUrl":"https://submission.nature.com/new-submission/530/3","title":"Multimedia Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"0d26fd77-6f74-4a8a-8b06-28e5dde136b3","owner":[],"postedDate":"June 25th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2026-01-12T16:09:45+00:00","versionOfRecord":{"articleIdentity":"rs-6897837","link":"https://doi.org/10.1007/s00530-025-02104-w","journal":{"identity":"multimedia-systems","isVorOnly":false,"title":"Multimedia Systems"},"publishedOn":"2026-01-08 15:58:58","publishedOnDateReadable":"January 8th, 2026"},"versionCreatedAt":"2025-06-25 06:24:01","video":"","vorDoi":"10.1007/s00530-025-02104-w","vorDoiUrl":"https://doi.org/10.1007/s00530-025-02104-w","workflowStages":[]},"version":"v1","identity":"rs-6897837","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6897837","identity":"rs-6897837","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}