GRAND-SLAM: Local Optimization for Globally Consistent Large-Scale Multi-Agent Gaussian SLAM

TL;DR

GRAND-SLAM introduces a multi-agent Gaussian SLAM method that enhances large-scale outdoor environment reconstruction with improved accuracy and consistency through local optimization and loop closure integration.

Contribution

It presents a novel collaborative Gaussian splatting SLAM framework that effectively handles large-scale outdoor environments with multi-agent cooperation.

Findings

28% higher PSNR on Replica dataset

91% lower multi-agent tracking error

Improved rendering quality in outdoor environments

Abstract

3D Gaussian splatting has emerged as an expressive scene representation for RGB-D visual SLAM, but its application to large-scale, multi-agent outdoor environments remains unexplored. Multi-agent Gaussian SLAM is a promising approach to rapid exploration and reconstruction of environments, offering scalable environment representations, but existing approaches are limited to small-scale, indoor environments. To that end, we propose Gaussian Reconstruction via Multi-Agent Dense SLAM, or GRAND-SLAM, a collaborative Gaussian splatting SLAM method that integrates i) an implicit tracking module based on local optimization over submaps and ii) an approach to inter- and intra-robot loop closure integrated into a pose-graph optimization framework. Experiments show that GRAND-SLAM provides state-of-the-art tracking performance and 28% higher PSNR than existing methods on the Replica indoor dataset, as well as 91% lower multi-agent tracking error and improved rendering over existing multi-agent methods on the large-scale, outdoor Kimera-Multi dataset.