MAGiC-SLAM: Multi-Agent Gaussian Globally Consistent SLAM

TL;DR

MAGiC-SLAM introduces a multi-agent SLAM system using Gaussian-based scene representation, achieving faster processing and improved accuracy in globally consistent mapping across multiple agents.

Contribution

It presents a novel rigidly deformable Gaussian scene representation and new tracking and map-merging methods for multi-agent SLAM.

Findings

More accurate than existing methods

Faster processing speeds

Effective in real-world and synthetic datasets

Abstract

Simultaneous localization and mapping (SLAM) systems with novel view synthesis capabilities are widely used in computer vision, with applications in augmented reality, robotics, and autonomous driving. However, existing approaches are limited to single-agent operation. Recent work has addressed this problem using a distributed neural scene representation. Unfortunately, existing methods are slow, cannot accurately render real-world data, are restricted to two agents, and have limited tracking accuracy. In contrast, we propose a rigidly deformable 3D Gaussian-based scene representation that dramatically speeds up the system. However, improving tracking accuracy and reconstructing a globally consistent map from multiple agents remains challenging due to trajectory drift and discrepancies across agents' observations. Therefore, we propose new tracking and map-merging mechanisms and integrate loop closure in the Gaussian-based SLAM pipeline. We evaluate MAGiC-SLAM on synthetic and real-world datasets and find it more accurate and faster than the state of the art.