RGB-Only Gaussian Splatting SLAM for Unbounded Outdoor Scenes

TL;DR

OpenGS-SLAM is a novel RGB-only SLAM system for outdoor scenes that uses pointmap regression for pose estimation and integrates 3D Gaussian Splatting, achieving high accuracy and state-of-the-art view synthesis.

Contribution

It introduces an RGB-only SLAM method for outdoor scenes using pointmap regression and end-to-end differentiable 3D Gaussian Splatting integration.

Findings

Reduces tracking error to 9.8% of previous methods

Achieves state-of-the-art results in novel view synthesis

Effective in unbounded outdoor scenes

Abstract

3D Gaussian Splatting (3DGS) has become a popular solution in SLAM, as it can produce high-fidelity novel views. However, previous GS-based methods primarily target indoor scenes and rely on RGB-D sensors or pre-trained depth estimation models, hence underperforming in outdoor scenarios. To address this issue, we propose a RGB-only gaussian splatting SLAM method for unbounded outdoor scenes--OpenGS-SLAM. Technically, we first employ a pointmap regression network to generate consistent pointmaps between frames for pose estimation. Compared to commonly used depth maps, pointmaps include spatial relationships and scene geometry across multiple views, enabling robust camera pose estimation. Then, we propose integrating the estimated camera poses with 3DGS rendering as an end-to-end differentiable pipeline. Our method achieves simultaneous optimization of camera poses and 3DGS scene parameters, significantly enhancing system tracking accuracy. Specifically, we also design an adaptive scale mapper for the pointmap regression network, which provides more accurate pointmap mapping to the 3DGS map representation. Our experiments on the Waymo dataset demonstrate that OpenGS-SLAM reduces tracking error to 9.8\% of previous 3DGS methods, and achieves state-of-the-art results in novel view synthesis. Project Page: https://3dagentworld.github.io/opengs-slam/