Compact Keyframe-Optimized Multi-Agent Gaussian Splatting SLAM

TL;DR

This paper introduces a compact multi-agent Gaussian Splatting SLAM system that significantly reduces communication bandwidth while maintaining high map quality, enabling practical multi-robot 3D mapping.

Contribution

It presents a novel Gaussian compaction method and a centralized loop closure approach with two modes, improving data efficiency in multi-agent SLAM.

Findings

Achieves up to 95% reduction in transmitted data compared to existing methods.

Maintains map fidelity despite Gaussian pruning and compaction.

Operates effectively in both rendered-depth and camera-depth modes.

Abstract

Efficient multi-agent 3D mapping is essential for robotic teams operating in unknown environments, but dense representations hinder real-time exchange over constrained communication links. In multi-agent Simultaneous Localization and Mapping (SLAM), systems typically rely on a centralized server to merge and optimize the local maps produced by individual agents. However, sharing these large map representations, particularly those generated by recent methods such as Gaussian Splatting, becomes a bottleneck in real-world scenarios with limited bandwidth. We present an improved multi-agent RGB-D Gaussian Splatting SLAM framework that reduces communication load while preserving map fidelity. First, we incorporate a compaction step into our SLAM system to remove redundant 3D Gaussians, without degrading the rendering quality. Second, our approach performs centralized loop closure computation without initial guess, operating in two modes: a pure rendered-depth mode that requires no data beyond the 3D Gaussians, and a camera-depth mode that includes lightweight depth images for improved registration accuracy and additional Gaussian pruning. Evaluation on both synthetic and real-world datasets shows up to 85-95\% reduction in transmitted data compared to state-of-the-art approaches in both modes, bringing 3D Gaussian multi-agent SLAM closer to practical deployment in real-world scenarios. Code: https://github.com/lemonci/coko-slam