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

2026-08-27

AI Summary

为解决多智能体在无RGB-D输入情况下进行3D重建的问题，提出CGS-SLAM方法，仅使用RGB和惯性数据实现协作式高斯点渲染SLAM。

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.

Problem

• SLAM
• RGB-D input
• 3D Gaussian Splatting
• multi-agent
• collaborative framework

Innovation

• Collaborative Gaussian Splatting
• multi-agent SLAM
• RGB and inertial data
• metric monocular depth estimator
• bidirectional communication