VPGS-SLAM: Voxel-based Progressive 3D Gaussian SLAM in Large-Scale Scenes

TL;DR

VPGS-SLAM introduces a scalable, robust 3D Gaussian SLAM framework for large-scale indoor and outdoor scenes, utilizing voxel-based mapping, 2D-3D fusion tracking, and loop closure for improved accuracy and consistency.

Contribution

It presents the first large-scale 3D Gaussian SLAM framework with novel voxel-based mapping, fusion tracking, and loop closure methods for enhanced robustness and scalability.

Findings

Effective large-scale scene mapping demonstrated.

Robust camera tracking in indoor and outdoor environments.

Improved pose accuracy and global consistency.

Abstract

3D Gaussian Splatting has recently shown promising results in dense visual SLAM. However, existing 3DGS-based SLAM methods are all constrained to small-room scenarios and struggle with memory explosion in large-scale scenes and long sequences. To this end, we propose VPGS-SLAM, the first 3DGS-based large-scale RGBD SLAM framework for both indoor and outdoor scenarios. We design a novel voxel-based progressive 3D Gaussian mapping method with multiple submaps for compact and accurate scene representation in large-scale and long-sequence scenes. This allows us to scale up to arbitrary scenes and improves robustness (even under pose drifts). In addition, we propose a 2D-3D fusion camera tracking method to achieve robust and accurate camera tracking in both indoor and outdoor large-scale scenes. Furthermore, we design a 2D-3D Gaussian loop closure method to eliminate pose drift. We further propose a submap fusion method with online distillation to achieve global consistency in large-scale scenes when detecting a loop. Experiments on various indoor and outdoor datasets demonstrate the superiority and generalizability of the proposed framework. The code will be open source on https://github.com/dtc111111/vpgs-slam.