Outram: One-shot Global Localization via Triangulated Scene Graph and Global Outlier Pruning

TL;DR

Outram is a hierarchical one-shot LiDAR localization method that uses 3D scene graph substructures for consistent correspondence search and outlier pruning, improving robustness in large-scale outdoor environments.

Contribution

It introduces a novel hierarchical approach that couples feature retrieval with correspondence refinement using scene graph substructures for robust localization.

Findings

Effective in large-scale outdoor datasets

Improves robustness against substructure ambiguities

Open-source implementation available

Abstract

One-shot LiDAR localization refers to the ability to estimate the robot pose from one single point cloud, which yields significant advantages in initialization and relocalization processes. In the point cloud domain, the topic has been extensively studied as a global descriptor retrieval (i.e., loop closure detection) and pose refinement (i.e., point cloud registration) problem both in isolation or combined. However, few have explicitly considered the relationship between candidate retrieval and correspondence generation in pose estimation, leaving them brittle to substructure ambiguities. To this end, we propose a hierarchical one-shot localization algorithm called Outram that leverages substructures of 3D scene graphs for locally consistent correspondence searching and global substructure-wise outlier pruning. Such a hierarchical process couples the feature retrieval and the correspondence extraction to resolve the substructure ambiguities by conducting a local-to-global consistency refinement. We demonstrate the capability of Outram in a variety of scenarios in multiple large-scale outdoor datasets. Our implementation is open-sourced: https://github.com/Pamphlett/Outram.