Multi-Agent Monocular Dense SLAM With 3D Reconstruction Priors

TL;DR

This paper introduces a multi-agent monocular dense SLAM system that leverages learned 3D priors for efficient and accurate 3D reconstruction and map fusion across agents, enhancing scalability and performance.

Contribution

It extends the MASt3R-SLAM system to multi-agent scenarios, enabling collaborative dense SLAM with improved efficiency and map consistency.

Findings

Achieves real-time performance with multi-agent setup.

Maintains high mapping accuracy comparable to single-agent systems.

Demonstrates improved computational efficiency over existing methods.

Abstract

Monocular Simultaneous Localization and Mapping (SLAM) aims to estimate a robot's pose while simultaneously reconstructing an unknown 3D scene using a single camera. While existing monocular SLAM systems generate detailed 3D geometry through dense scene representations, they are computationally expensive due to the need for iterative optimization. To address this challenge, MASt3R-SLAM utilizes learned 3D reconstruction priors, enabling more efficient and accurate estimation of both 3D structures and camera poses. However, MASt3R-SLAM is limited to single-agent operation. In this paper, we extend MASt3R-SLAM to introduce the first multi-agent monocular dense SLAM system. Each agent performs local SLAM using a 3D reconstruction prior, and their individual maps are fused into a globally consistent map through a loop-closure-based map fusion mechanism. Our approach improves computational efficiency compared to state-of-the-art methods, while maintaining similar mapping accuracy when evaluated on real-world datasets.