Coarse-to-Fine Monocular Re-Localization in OpenStreetMap via Semantic Alignment

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zou, Yuchen, Hu, Xiao, Zhong, Dexing, Tang, Yuqing
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910037800124416
author Zou, Yuchen
Hu, Xiao
Zhong, Dexing
Tang, Yuqing
author_facet Zou, Yuchen
Hu, Xiao
Zhong, Dexing
Tang, Yuqing
contents Monocular re-localization plays a crucial role in enabling intelligent agents to achieve human-like perception. However, traditional methods rely on dense maps, which face scalability limitations and privacy risks. OpenStreetMap (OSM), as a lightweight map that protects privacy, offers semantic and geometric information with global scalability. Nonetheless, there are still challenges in using OSM for localization: the inherent cross-modal discrepancies between natural images and OSM, as well as the high computational cost of global map-based localization. In this paper, we propose a hierarchical search framework with semantic alignment for localization in OSM. First, the semantic awareness capability of DINO-ViT is utilised to deconstruct visual elements to establish semantic relationships with OSM. Second, a coarse-to-fine search paradigm is designed to replace global dense matching, enabling efficient progressive refinement. Extensive experiments demonstrate that our method significantly improves both localization accuracy and speed. When trained on a single dataset, the 3° orientation recall of our method even outperforms the 5° recall of state-of-the-art methods.
format Preprint
id arxiv_https___arxiv_org_abs_2603_01613
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Coarse-to-Fine Monocular Re-Localization in OpenStreetMap via Semantic Alignment
Zou, Yuchen
Hu, Xiao
Zhong, Dexing
Tang, Yuqing
Computer Vision and Pattern Recognition
Monocular re-localization plays a crucial role in enabling intelligent agents to achieve human-like perception. However, traditional methods rely on dense maps, which face scalability limitations and privacy risks. OpenStreetMap (OSM), as a lightweight map that protects privacy, offers semantic and geometric information with global scalability. Nonetheless, there are still challenges in using OSM for localization: the inherent cross-modal discrepancies between natural images and OSM, as well as the high computational cost of global map-based localization. In this paper, we propose a hierarchical search framework with semantic alignment for localization in OSM. First, the semantic awareness capability of DINO-ViT is utilised to deconstruct visual elements to establish semantic relationships with OSM. Second, a coarse-to-fine search paradigm is designed to replace global dense matching, enabling efficient progressive refinement. Extensive experiments demonstrate that our method significantly improves both localization accuracy and speed. When trained on a single dataset, the 3° orientation recall of our method even outperforms the 5° recall of state-of-the-art methods.
title Coarse-to-Fine Monocular Re-Localization in OpenStreetMap via Semantic Alignment
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.01613