3DGS_LSR:Large_Scale Relocation for Autonomous Driving Based on 3D Gaussian Splatting

TL;DR

This paper introduces 3DGS-LSR, a novel large-scale relocalization framework that achieves centimeter-level accuracy using only monocular RGB images, leveraging 3D Gaussian Splatting and multi-sensor data for reliable urban autonomous navigation.

Contribution

The paper presents a new relocalization method combining 3D Gaussian Splatting with iterative optimization, enabling high-accuracy localization with minimal sensor input in large outdoor scenes.

Findings

Achieves average localization errors of 0.026m, 0.029m, and 0.081m in different urban environments.

Outperforms existing methods in accuracy while using only monocular RGB images.

Demonstrates real-time capability suitable for autonomous navigation.

Abstract

In autonomous robotic systems, precise localization is a prerequisite for safe navigation. However, in complex urban environments, GNSS positioning often suffers from signal occlusion and multipath effects, leading to unreliable absolute positioning. Traditional mapping approaches are constrained by storage requirements and computational inefficiency, limiting their applicability to resource-constrained robotic platforms. To address these challenges, we propose 3DGS-LSR: a large-scale relocalization framework leveraging 3D Gaussian Splatting (3DGS), enabling centimeter-level positioning using only a single monocular RGB image on the client side. We combine multi-sensor data to construct high-accuracy 3DGS maps in large outdoor scenes, while the robot-side localization requires just a standard camera input. Using SuperPoint and SuperGlue for feature extraction and matching, our core innovation is an iterative optimization strategy that refines localization results through step-by-step rendering, making it suitable for real-time autonomous navigation. Experimental validation on the KITTI dataset demonstrates our 3DGS-LSR achieves average positioning accuracies of 0.026m, 0.029m, and 0.081m in town roads, boulevard roads, and traffic-dense highways respectively, significantly outperforming other representative methods while requiring only monocular RGB input. This approach provides autonomous robots with reliable localization capabilities even in challenging urban environments where GNSS fails.