3D Gaussian Splatting aided Localization for Large and Complex Indoor-Environments
This work addresses localization failures in large, complex indoor settings, such as industrial environments, but is incremental as it builds on existing methods by adding rendered data.
The paper tackles the problem of visual localization in challenging indoor environments by enhancing reference data with rendered images from a 3D Gaussian Splatting map, resulting in significant improvements in accuracy and reliability for both geometry-based and Scene Coordinate Regression methods.
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.