MapLocNet: Coarse-to-Fine Feature Registration for Visual Re-Localization in Navigation Maps

TL;DR

MapLocNet introduces a transformer-based coarse-to-fine feature registration approach for visual re-localization in navigation maps, achieving real-time, accurate, and scalable localization without relying on expensive HD maps in urban driving environments.

Contribution

The paper presents a novel neural re-localization method using transformer-based registration that outperforms existing approaches in accuracy and speed, eliminating the need for HD maps.

Findings

Nearly 10%/20% improvement in localization accuracy on nuScenes and Argoverse datasets.

30/16 FPS performance in single-view and surround-view settings.

Outperforms state-of-the-art OrienterNet in accuracy and inference speed.

Abstract

Robust localization is the cornerstone of autonomous driving, especially in challenging urban environments where GPS signals suffer from multipath errors. Traditional localization approaches rely on high-definition (HD) maps, which consist of precisely annotated landmarks. However, building HD map is expensive and challenging to scale up. Given these limitations, leveraging navigation maps has emerged as a promising low-cost alternative for localization. Current approaches based on navigation maps can achieve highly accurate localization, but their complex matching strategies lead to unacceptable inference latency that fails to meet the real-time demands. To address these limitations, we propose a novel transformer-based neural re-localization method. Inspired by image registration, our approach performs a coarse-to-fine neural feature registration between navigation map and visual bird's-eye view features. Our method significantly outperforms the current state-of-the-art OrienterNet on both the nuScenes and Argoverse datasets, which is nearly 10%/20% localization accuracy and 30/16 FPS improvement on single-view and surround-view input settings, separately. We highlight that our research presents an HD-map-free localization method for autonomous driving, offering cost-effective, reliable, and scalable performance in challenging driving environments.