CGS-SLAM: Collaborative Gaussian Splatting based SLAM for Multi-Agent Reconstruction

• URL: http://arxiv.org/abs/2608.26868v1
• Date: Thu, 27 Aug 2026 09:31:18 GMT
• Title: CGS-SLAM: Collaborative Gaussian Splatting based SLAM for Multi-Agent Reconstruction
• Abstract summary: CGS-SLAM is a hybrid decentralized/centralized system enabling multi-agent 3DGS SLAM using only RGB and inertial data.<n>Keyframe encodings are shared among agents, enabling dynamic keyframing in regions of spatial overlaps.<n>Experiments on multiple datasets demonstrate competitive tracking performance, improved quality over state-of-the-art methods, and accurate submap alignment.
• Score: 7.022188673549244
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Recent advances in SLAM have leveraged 3DGS for photorealistic reconstruction and novel view synthesis. However, most methods rely on RGB-D input, which is unavailable on consumer-grade smartphones, and few integrate 3DGS within a collaborative framework. Therefore, we present CGS-SLAM, a hybrid decentralized/centralized system enabling multi-agent 3DGS SLAM using only RGB and inertial data. Each agent performs local tracking with inertial data as a motion prior and reconstructs a scaled map using a metric monocular depth estimator (Depth Pro). Keyframe encodings are shared among agents, enabling dynamic keyframing in regions of spatial overlaps with other agents, enhancing submap alignment. Afterwards, a central server aligns submaps using VGGT as a view alignment model. This bidirectional communication keeps communication cost low during mapping and global reconstruction in difficult GNSS-denied environments. Experiments on multiple datasets demonstrate competitive tracking performance, improved rendering quality over state-of-the-art methods, and accurate submap alignment.

Related papers

• MAGS-SLAM: Monocular Multi-Agent Gaussian Splatting SLAM for Geometrically and Photometrically Consistent Reconstruction [14.638296790824421]
  Collaborative 3D reconstruction from multiple agents enables rapid large-scale scene capture for virtual production and cooperative multi-robot exploration.<n>Most of the existing multi-agent Gaussian SLAM methods still rely on RGB-D sensors to obtain metric depth and simplify cross-agent alignment.<n>We propose MAGS-SLAM, the first RGB-only multi-agent 3DGS SLAM framework for collaborative scene reconstruction.
  arXiv  Detail & Related papers  (2026-05-11T15:57:13Z)
• Compact Keyframe-Optimized Multi-Agent Gaussian Splatting SLAM [4.458834881246724]
  Multi-agent 3D mapping is essential for robotic teams operating in unknown environments, but dense representations hinder real-time exchange.<n>We present an improved multi-agent RGB-D Gaussian Splatting SLAM framework that reduces communication load while preserving map fidelity.
  arXiv  Detail & Related papers  (2026-04-01T12:11:20Z)
• LG-HCC: Local Geometry-Aware Hierarchical Context Compression for 3D Gaussian Splatting [77.81227097905865]
  Anchor-based 3DGS compression schemes reduce gaussian redundancy through some advanced context models.<n>We propose a Local Geometry-aware Hierarchical Context Compression framework for 3DGS that incorporates inter-anchor geometric correlations into anchor pruning and entropy coding for compact representation.<n>Experiments show that LG-HCC effectively alleviates structural preservation issues,achieving superior geometric integrity and rendering fidelity while reducing storage by up to 30.85x compared to the Scaffold-GS baseline on the Mip-NeRF360 dataset.
  arXiv  Detail & Related papers  (2026-03-30T13:39:35Z)
• VarSplat: Uncertainty-aware 3D Gaussian Splatting for Robust RGB-D SLAM [2.5823344978857388]
  VarSplat is an uncertainty-aware 3DGS-SLAM system that explicitly learns per-splat appearance variance.<n>We show that VarSplat improves robustness and competitive or superior tracking, mapping, and novel view rendering compared to existing studies for dense RGB-D SLAM.
  arXiv  Detail & Related papers  (2026-03-10T13:42:58Z)
• SING3R-SLAM: Submap-based Indoor Monocular Gaussian SLAM with 3D Reconstruction Priors [80.51557267896938]
  SING3R-SLAM is a globally consistent and compact Gaussian-based dense RGB SLAM framework.<n>We show that SING3R-SLAM achieves state-of-the-art tracking, 3D reconstruction, and novel view rendering, resulting in over 12% improvement in tracking and producing finer, more detailed geometry.
  arXiv  Detail & Related papers  (2025-11-21T12:40:55Z)
• MCGS-SLAM: A Multi-Camera SLAM Framework Using Gaussian Splatting for High-Fidelity Mapping [52.99503784067417]
  We present MCGS-SLAM, the first purely RGB-based multi-camera SLAM system built on 3D Gaussian Splatting (3DGS)<n>A multi-camera bundle adjustment (MCBA) jointly refines poses and depths via dense photometric and geometric residuals, while a scale consistency module enforces metric alignment across views.<n>Experiments on synthetic and real-world datasets show that MCGS-SLAM consistently yields accurate trajectories and photorealistic reconstructions.
  arXiv  Detail & Related papers  (2025-09-17T17:27:53Z)
• A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation [66.62489208150681]
  3D Gaussian Splatting (3DGS) has emerged as a powerful alternative to Neural Radiance Fields (NeRF) for 3D scene representation.<n>This survey provides a comprehensive overview of recent progress in 3DGS applications.
  arXiv  Detail & Related papers  (2025-08-13T17:44:39Z)
• IG-SLAM: Instant Gaussian SLAM [6.228980850646457]
  3D Gaussian Splatting has recently shown promising results as an alternative scene representation in SLAM systems. We present IG-SLAM, a dense RGB-only SLAM system that employs robust Dense-SLAM methods for tracking and combines them with Gaussian Splatting. We demonstrate competitive performance with state-of-the-art RGB-only SLAM systems while achieving faster operation speeds.
  arXiv  Detail & Related papers  (2024-08-02T09:07:31Z)
• Splat-SLAM: Globally Optimized RGB-only SLAM with 3D Gaussians [87.48403838439391]
  3D Splatting has emerged as a powerful representation of geometry and appearance for RGB-only dense Simultaneous SLAM. We propose the first RGB-only SLAM system with a dense 3D Gaussian map representation. Our experiments on the Replica, TUM-RGBD, and ScanNet datasets indicate the effectiveness of globally optimized 3D Gaussians.
  arXiv  Detail & Related papers  (2024-05-26T12:26:54Z)
• RGBD GS-ICP SLAM [1.3108652488669732]
  We propose a novel dense representation SLAM approach with a fusion of Generalized Iterative Closest Point (G-ICP) and 3D Gaussian Splatting (3DGS) Experimental results demonstrate the effectiveness of our approach, showing an incredibly fast speed up to 107 FPS.
  arXiv  Detail & Related papers  (2024-03-19T08:49:48Z)
• NICER-SLAM: Neural Implicit Scene Encoding for RGB SLAM [111.83168930989503]
  NICER-SLAM is a dense RGB SLAM system that simultaneously optimize for camera poses and a hierarchical neural implicit map representation. We show strong performance in dense mapping, tracking, and novel view synthesis, even competitive with recent RGB-D SLAM systems.
  arXiv  Detail & Related papers  (2023-02-07T17:06:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.