G-EDF-Loc: 3D Continuous Gaussian Distance Field for Robust Gradient-Based 6DoF Localization

TL;DR

This paper introduces G-EDF-Loc, a robust 6-DoF localization method using a novel continuous 3D distance field representation that enables high-accuracy, real-time spatial reconstruction and localization.

Contribution

The paper proposes G-EDF, a new continuous Gaussian-based 3D distance field, and integrates it into a CPU-based scan-to-map registration pipeline for improved robustness and efficiency.

Findings

G-EDF-Loc achieves high-fidelity localization in large-scale datasets.

The method remains resilient under severe odometry degradation.

It performs well even without IMU priors.

Abstract

This paper presents a robust 6-DoF localization framework based on a direct, CPU-based scan-to-map registration pipeline. The system leverages G-EDF, a novel continuous and memory-efficient 3D distance field representation. The approach models the Euclidean Distance Field (EDF) using a Block-Sparse Gaussian Mixture Model with adaptive spatial partitioning, ensuring $C^1$ continuity across block transitions and mitigating boundary artifacts. By leveraging the analytical gradients of this continuous map, which maintain Eikonal consistency, the proposed method achieves high-fidelity spatial reconstruction and real-time localization. Experimental results on large-scale datasets demonstrate that G-EDF-Loc performs competitively against state-of-the-art methods, exhibiting exceptional resilience even under severe odometry degradation or in the complete absence of IMU priors.