[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-84999-en":3,"doc-seo-84999-105":29,"detail-sidebar-cat-0-en-105":90},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},84999,13056703019404,"Miles","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",6,"Technology","GeoGS-SLAM: Geometry-Only Gaussian Splatting for Dense Monocular SLAM","Dense visual simultaneous localization and mapping (SLAM) requires accurate camera pose estimation and dense 3D scene reconstruction. While 3D Gaussian Splatting (3DGS) has enabled dense SLAM, current frameworks couple appearance and geometry, despite robotics tasks relying more on spatial structure than photorealistic rendering. Geometry-only Gaussian Splatting (GeoGS) reconstructs geometry without appearance modeling by retaining only position, rotation, scale, and opacity, reducing parameters and Gaussians. GeoGS-SLAM adds training with geometric and photometric supervision and an update strategy for loop closure or global BA to align the map globally while preserving local coherence, yielding faster convergence and improved robustness to illumination changes.","GeoGS-SLAM: Geometry-Only Gaussian Splatting for Dense  \nMonocular SLAM  \nLipu Zhou∗1, Yaoyun Kang 1 , Junxiang Pang 1 , Shengkai Sun 1 , Tingting Bao 1 , Kehan Wang 1  \narXiv :2607 .07452v 1 [ cs .RO] 8 Jul 2026  \nAbstract—Dense visual Simultaneous Localization and Mapping (SLAM) is a fundamental problem in robotics. Recent advances in 3D Gaussian Splatting (3DGS) have demonstrated its potential for dense SLAM. Existing 3DGS frameworks focus on both appearance and geometry modeling. However, scene geometry is typically more critical for SLAM than novel view synthesis because downstream robotic tasks, such as navigation and obstacle avoidance, rely primarily on accurate spatial geometry rather than photorealistic rendering. This observation raises a natural question: Is it feasible for 3DGS to perform 3D reconstruction without scene appearance modeling? Motivated by this, we propose Geometry-only Gaussian Splatting (GeoGS), which directly reconstructs scene geometry, and further present GeoGS-SLAM, a dense visual SLAM system built upon this representation. Specifically, GeoGS retains only spatial parameters (position, rotation, scale, and opacity) to reduce the number of per-primitive parameters by over 80% . In contrast to existing 3DGS methods, GeoGS focuses solely on geometric reconstruction, which significantly reduces the number of Gaussian primitives, accelerates geometric convergence, and enhances robustness to illumination variations. In addition, we present an effective training framework that optimizes the Gaussian primitives via single-view and multi-view geometric and photometric supervision, and speeds up geometry convergence with a localplane driven initialization that better aligns primitives with local structures. Furthermore, we introduce a map update strategy for loop closure or global Bundle Adjustment (BA) that globally transforms the Gaussian map to align it with the corrected pose estimates while preserving local structural coherence, thereby preventing map tearing caused by inconsistent per-viewpoint pose corrections in existing methods. Extensive experiments on synthetic and real-world benchmarks demonstrate that our method outperforms state-of-the-art methods in terms of online mapping efficiency and geometric reconstruction quality. Our code will be made available.  \nIndex Terms—Visual SLAM, Gaussian Splatting, dense reconstruction  \nI. INTRODUCTION  \nDense visual Simultaneous Localization and Mapping (SLAM), which jointly estimates camera poses and reconstructs a dense 3D map of the environment, is a fundamental problem in robotics [1] . Recently, 3D Gaussian Splatting (3DGS) [2] introduces a new paradigm for 3D reconstruction. Through explicit Gaussian-based scene representation and differentiable rasterization, 3DGS has demonstrated remarkable performance in novel view synthesis (NVS) and has emerged as a promising approach for dense visual SLAM [3] .  \n*Corresponding author  \n1The authors are with the School of Instrument Science and Optoelectronics Engineering, Beihang University, Beijing 100191, China (email: {zhoulipu, KangYY, pangjunxiang, 22373368, btt2022, [25171012](25171012}@buaa.edu.cn)[}](25171012}@buaa.edu.cn)[@buaa.edu.cn](25171012}@buaa.edu.cn))  \nFig. 1. Illustration of the characteristics of GeoGS and the performance of GeoGS-SLAM. (a) Qualitative comparison of geometric reconstruction. GeoGS-SLAM recovers much cleaner scene geometry compared to the baseline method. (b) Per-primitive parameter efficiency. By retaining only the geometr-related parameters (µ,q,s,α), GeoGS remains only 17% of the parameters required by a standard 3DGS primitive. (c) Model efficiency of the reconstructed Gaussian map. In addition to the reduction of per-primitive parameters, GeoGS represents the scene with substantially fewer Gaussians, requiring only 28k Gaussian primitives, compared with 198k for 2DGS, 193k for PGSR, and 107k for QGS.  \nFollowing the success of 3DGS and its variants in NVS [4]–[7], a ","cbCaibpFgPbMyDOi","https://ap.wps.com/l/cbCaibpFgPbMyDOi","pdf",28251880,1,17,"English","en",105,"# Introduction\n## Dense visual SLAM and 3D Gaussian Splatting\n## Motivation for geometry-only reconstruction\n## Challenges in global map correction","[{\"question\":\"What problem does GeoGS-SLAM address in dense monocular SLAM?\",\"answer\":\"GeoGS-SLAM targets dense visual SLAM where robust and accurate 3D geometry reconstruction is essential for robotics, not just photorealistic rendering.\"},{\"question\":\"How does GeoGS differ from standard 3D Gaussian Splatting?\",\"answer\":\"GeoGS keeps only geometric spatial parameters—position, rotation, scale, and opacity—reducing per-primitive parameters and focusing training on geometric reconstruction rather than appearance modeling.\"},{\"question\":\"How does GeoGS-SLAM handle global corrections from loop closure or global bundle adjustment?\",\"answer\":\"It applies a map update strategy that globally transforms the Gaussian map to match corrected pose estimates while preserving local structural coherence, preventing map tearing from inconsistent per-view corrections.\"}]",1784200137,43,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"geogs-slam-geometry-only-gaussian-splatting-for-dense-monocular-slam","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/technology/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/geogs-slam-geometry-only-gaussian-splatting-for-dense-monocular-slam/84999/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What problem does GeoGS-SLAM address in dense monocular SLAM?","Question",{"text":74,"@type":75},"GeoGS-SLAM targets dense visual SLAM where robust and accurate 3D geometry reconstruction is essential for robotics, not just photorealistic rendering.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How does GeoGS differ from standard 3D Gaussian Splatting?",{"text":79,"@type":75},"GeoGS keeps only geometric spatial parameters—position, rotation, scale, and opacity—reducing per-primitive parameters and focusing training on geometric reconstruction rather than appearance modeling.",{"name":81,"@type":72,"acceptedAnswer":82},"How does GeoGS-SLAM handle global corrections from loop closure or global bundle adjustment?",{"text":83,"@type":75},"It applies a map update strategy that globally transforms the Gaussian map to match corrected pose estimates while preserving local structural coherence, preventing map tearing from inconsistent per-view corrections.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,112,117,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":110,"slug":111},50,"technology",{"id":113,"doc_module":4,"doc_module_name":45,"category_name":114,"show_sort_weight":115,"slug":116},7,"Healthcare",40,"healthcare",{"id":118,"doc_module":4,"doc_module_name":45,"category_name":119,"show_sort_weight":120,"slug":121},8,"Research & Report",30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":105,"slug":137},19,"General","general"]