MAGS-SLAM: Monocular Multi-Agent Gaussian Splatting SLAM for Geometrically and Photometrically Consistent Reconstruction

2026-05-11

AI Summary

This work addresses the limitations of existing RGB-D-based multi-agent Gaussian SLAM systems, which rely on depth sensors and are thus unsuitable for lightweight, low-cost platforms. We propose the first purely RGB-based multi-agent 3D Gaussian Splatting SLAM framework, wherein each agent independently constructs a monocular Gaussian submap and achieves efficient communication and globally consistent reconstruction through compact subgraph summaries. Key innovations include a geometry-appearance joint loop closure verification mechanism, an occupancy-aware Gaussian fusion strategy to mitigate monocular scale ambiguity, and a low-bandwidth collaboration protocol. Experiments demonstrate that our method achieves tracking accuracy on par with state-of-the-art RGB-D approaches and delivers comparable or even superior rendering quality on both synthetic and real-world datasets. We also introduce the ReplicaMultiagent Plus benchmark for evaluation.

Abstract

Collaborative photorealistic 3D reconstruction from multiple agents enables rapid large-scale scene capture for virtual production and cooperative multi-robot exploration. While recent 3D Gaussian Splatting (3DGS) SLAM algorithms can generate high-fidelity real-time mapping, most of the existing multi-agent Gaussian SLAM methods still rely on RGB-D sensors to obtain metric depth and simplify cross-agent alignment, which limits the deployment on lightweight, low-cost, or power-constrained robotic platforms. To address this challenge, we propose MAGS-SLAM, the first RGB-only multi-agent 3DGS SLAM framework for collaborative scene reconstruction. Each agent independently builds local monocular Gaussian submaps and transmits compact submap summaries rather than raw observations or dense maps. To facilitate robust collaboration in the presence of monocular scale ambiguity, our framework integrates compact submap communication, geometry- and appearance-aware loop verification, and occupancy-aware Gaussian fusion, enabling coherent global reconstruction without active depth sensors. We further introduce ReplicaMultiagent Plus benchmark for evaluating collaborative Gaussian SLAM. Intensive experiments on synthetic and real-world datasets show that MAGS-SLAM achieves competitive tracking accuracy and comparable or superior rendering quality to state-of-the-art RGB-D collaborative Gaussian SLAM methods while relying only RGB images.

Problem

• multi-agent SLAM
• monocular reconstruction
• 3D Gaussian Splatting
• RGB-only sensing
• collaborative mapping

Innovation

• Monocular SLAM
• Multi-Agent Collaboration
• 3D Gaussian Splatting
• Photometric Consistency
• Compact Submap Communication