GeomGS: LiDAR-Guided Geometry-Aware Gaussian Splatting for Robot Localization

TL;DR

GeomGS introduces a LiDAR-guided, geometry-aware Gaussian Splatting method that enhances 3D mapping and localization accuracy by integrating LiDAR data with probabilistic constraints, outperforming existing approaches.

Contribution

It proposes a novel probabilistic integration of LiDAR data into 3D Gaussian primitives with a geometric confidence score, improving map accuracy and localization.

Findings

State-of-the-art geometric accuracy on benchmarks

Improved localization performance

Enhanced photometric rendering quality

Abstract

Mapping and localization are crucial problems in robotics and autonomous driving. Recent advances in 3D Gaussian Splatting (3DGS) have enabled precise 3D mapping and scene understanding by rendering photo-realistic images. However, existing 3DGS methods often struggle to accurately reconstruct a 3D map that reflects the actual scale and geometry of the real world, which degrades localization performance. To address these limitations, we propose a novel 3DGS method called Geometry-Aware Gaussian Splatting (GeomGS). This method fully integrates LiDAR data into 3D Gaussian primitives via a probabilistic approach, as opposed to approaches that only use LiDAR as initial points or introduce simple constraints for Gaussian points. To this end, we introduce a Geometric Confidence Score (GCS), which identifies the structural reliability of each Gaussian point. The GCS is optimized simultaneously with Gaussians under probabilistic distance constraints to construct a precise structure. Furthermore, we propose a novel localization method that fully utilizes both the geometric and photometric properties of GeomGS. Our GeomGS demonstrates state-of-the-art geometric and localization performance across several benchmarks, while also improving photometric performance.