Outdoor Monocular SLAM with Global Scale-Consistent 3D Gaussian Pointmaps

TL;DR

This paper introduces S3PO-GS, a robust outdoor monocular SLAM method using 3D Gaussian pointmaps that achieves high accuracy and prevents scale drift in complex outdoor environments.

Contribution

It presents a novel self-consistent tracking module and a patch-based dynamic mapping approach that incorporate geometric priors and eliminate scale ambiguity in outdoor SLAM.

Findings

Outperforms existing 3DGS SLAM methods in tracking accuracy.

Achieves state-of-the-art results in novel view synthesis on outdoor datasets.

Effectively prevents scale drift in complex outdoor scenes.

Abstract

3D Gaussian Splatting (3DGS) has become a popular solution in SLAM due to its high-fidelity and real-time novel view synthesis performance. However, some previous 3DGS SLAM methods employ a differentiable rendering pipeline for tracking, lack geometric priors in outdoor scenes. Other approaches introduce separate tracking modules, but they accumulate errors with significant camera movement, leading to scale drift. To address these challenges, we propose a robust RGB-only outdoor 3DGS SLAM method: S3PO-GS. Technically, we establish a self-consistent tracking module anchored in the 3DGS pointmap, which avoids cumulative scale drift and achieves more precise and robust tracking with fewer iterations. Additionally, we design a patch-based pointmap dynamic mapping module, which introduces geometric priors while avoiding scale ambiguity. This significantly enhances tracking accuracy and the quality of scene reconstruction, making it particularly suitable for complex outdoor environments. Our experiments on the Waymo, KITTI, and DL3DV datasets demonstrate that S3PO-GS achieves state-of-the-art results in novel view synthesis and outperforms other 3DGS SLAM methods in tracking accuracy. Project page: https://3dagentworld.github.io/S3PO-GS/.