# LoGS: Visual Localization via Gaussian Splatting with Fewer Training Images

Source: [LoGS: Visual Localization via Gaussian Splatting with Fewer Training Images](<https://www.sota2.com/research/paper/68fa75341e209131cea66666>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T03:29:07.731Z

Authors: Yuzhou Cheng, Jianhao Jiao, Yue Wang, Dimitrios Kanoulas

Published: 2024-10-15T11:17:18.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Visual Localization on 7Scenes Pumpkin](<https://www.sota2.com/research/sota/visual-localization-on-7scenes-pumpkin.md>): Visual Localization; 7Scenes Pumpkin; Median Translation Error (cm): 0.7.

- [Visual Localization on 7Scenes RedKitchen](<https://www.sota2.com/research/sota/visual-localization-on-7scenes-redkitchen.md>): Visual Localization; 7Scenes RedKitchen; Median Translation Error (cm): 0.5.

- [Visual Relocalization on Cambridge Landmarks (test)](<https://www.sota2.com/research/sota/visual-relocalization-on-cambridge-landmarks-test.md>): Visual Relocalization; Cambridge Landmarks (test); College Median Translation Error (cm): 11.

- [Visual Localization on 7Scenes Office](<https://www.sota2.com/research/sota/visual-localization-on-7scenes-office.md>): Visual Localization; 7Scenes (Office); Median Translation Error (cm): 0.7.

- [Relocalization on 7-Scenes Average](<https://www.sota2.com/research/sota/relocalization-on-7-scenes-average.md>): Relocalization; 7-Scenes Average; Median Translation Error (cm): 0.76.

- [Visual Localization on 7Scenes Fire](<https://www.sota2.com/research/sota/visual-localization-on-7scenes-fire.md>): Visual Localization; 7Scenes Fire; Median Translation Error (cm): 0.6.

- [Visual Localization on 7Scenes Stairs](<https://www.sota2.com/research/sota/visual-localization-on-7scenes-stairs.md>): Visual Localization; 7Scenes Stairs; Median Translation Error (cm): 1.6.

- [Visual Localization on 7Scenes Chess](<https://www.sota2.com/research/sota/visual-localization-on-7scenes-chess.md>): Visual Localization; 7Scenes Chess; Median Translation Error (cm): 0.4.

- [Visual Localization on 7Scenes Heads](<https://www.sota2.com/research/sota/visual-localization-on-7scenes-heads.md>): Visual Localization; 7Scenes Heads; Median Translation Error (cm): 0.5.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2410.11505>)

[PDF](<https://arxiv.org/pdf/2410.11505.pdf>)