3D Gaussian Splatting aided Localization for Large and Complex Indoor-Environments

TL;DR

This paper enhances visual localization accuracy in complex indoor environments by integrating rendered images from a 3D Gaussian Splatting map, significantly improving existing methods' reliability.

Contribution

It introduces a novel approach of augmenting reference data with rendered images from 3D Gaussian Splatting to boost localization performance.

Findings

Improved localization accuracy with rendered images.

Enhanced reliability of existing visual localization methods.

Effective in large industrial environments.

Abstract

The field of visual localization has been researched for several decades and has meanwhile found many practical applications. Despite the strong progress in this field, there are still challenging situations in which established methods fail. We present an approach to significantly improve the accuracy and reliability of established visual localization methods by adding rendered images. In detail, we first use a modern visual SLAM approach that provides a 3D Gaussian Splatting (3DGS) based map to create reference data. We demonstrate that enriching reference data with images rendered from 3DGS at randomly sampled poses significantly improves the performance of both geometry-based visual localization and Scene Coordinate Regression (SCR) methods. Through comprehensive evaluation in a large industrial environment, we analyze the performance impact of incorporating these additional rendered views.