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

TL;DR

MAGS-SLAM is a novel RGB-only multi-agent SLAM framework that enables high-fidelity 3D scene reconstruction without depth sensors, suitable for lightweight robotic platforms.

Contribution

It introduces the first RGB-only multi-agent Gaussian SLAM system with compact submap communication and robust loop verification for collaborative scene reconstruction.

Findings

Achieves competitive accuracy with RGB-only data

Provides high-quality 3D reconstructions comparable to RGB-D methods

Introduces a new benchmark for multi-agent Gaussian SLAM 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.