LoGS: Visual Localization via Gaussian Splatting with Fewer Training Images

TL;DR

LoGS introduces a novel Gaussian Splatting-based scene representation for visual localization, achieving state-of-the-art accuracy with fewer training images and robust performance in challenging conditions.

Contribution

The paper presents LoGS, a new localization pipeline using Gaussian Splatting for scene representation, enabling high-quality view synthesis and accurate pose estimation with limited images.

Findings

Achieves state-of-the-art accuracy on large-scale datasets.

Robust performance under few-shot conditions.

Effective scene representation with Gaussian Splatting.

Abstract

Visual localization involves estimating a query image's 6-DoF (degrees of freedom) camera pose, which is a fundamental component in various computer vision and robotic tasks. This paper presents LoGS, a vision-based localization pipeline utilizing the 3D Gaussian Splatting (GS) technique as scene representation. This novel representation allows high-quality novel view synthesis. During the mapping phase, structure-from-motion (SfM) is applied first, followed by the generation of a GS map. During localization, the initial position is obtained through image retrieval, local feature matching coupled with a PnP solver, and then a high-precision pose is achieved through the analysis-by-synthesis manner on the GS map. Experimental results on four large-scale datasets demonstrate the proposed approach's SoTA accuracy in estimating camera poses and robustness under challenging few-shot conditions.