A Unified Hierarchical Framework for Fine-grained Cross-view Geo-localization over Large-scale Scenarios

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Song, Zhuo, Zhang, Ye, Li, Kunhong, Wang, Longguang, Guo, Yulan
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909607770718208
author Song, Zhuo
Zhang, Ye
Li, Kunhong
Wang, Longguang
Guo, Yulan
author_facet Song, Zhuo
Zhang, Ye
Li, Kunhong
Wang, Longguang
Guo, Yulan
contents Cross-view geo-localization is a promising solution for large-scale localization problems, requiring the sequential execution of retrieval and metric localization tasks to achieve fine-grained predictions. However, existing methods typically focus on designing standalone models for these two tasks, resulting in inefficient collaboration and increased training overhead. In this paper, we propose UnifyGeo, a novel unified hierarchical geo-localization framework that integrates retrieval and metric localization tasks into a single network. Specifically, we first employ a unified learning strategy with shared parameters to jointly learn multi-granularity representation, facilitating mutual reinforcement between these two tasks. Subsequently, we design a re-ranking mechanism guided by a dedicated loss function, which enhances geo-localization performance by improving both retrieval accuracy and metric localization references. Extensive experiments demonstrate that UnifyGeo significantly outperforms the state-of-the-arts in both task-isolated and task-associated settings. Remarkably, on the challenging VIGOR benchmark, which supports fine-grained localization evaluation, the 1-meter-level localization recall rate improves from 1.53\% to 39.64\% and from 0.43\% to 25.58\% under same-area and cross-area evaluations, respectively. Code will be made publicly available.
format Preprint
id arxiv_https___arxiv_org_abs_2505_07622
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Unified Hierarchical Framework for Fine-grained Cross-view Geo-localization over Large-scale Scenarios
Song, Zhuo
Zhang, Ye
Li, Kunhong
Wang, Longguang
Guo, Yulan
Computer Vision and Pattern Recognition
Cross-view geo-localization is a promising solution for large-scale localization problems, requiring the sequential execution of retrieval and metric localization tasks to achieve fine-grained predictions. However, existing methods typically focus on designing standalone models for these two tasks, resulting in inefficient collaboration and increased training overhead. In this paper, we propose UnifyGeo, a novel unified hierarchical geo-localization framework that integrates retrieval and metric localization tasks into a single network. Specifically, we first employ a unified learning strategy with shared parameters to jointly learn multi-granularity representation, facilitating mutual reinforcement between these two tasks. Subsequently, we design a re-ranking mechanism guided by a dedicated loss function, which enhances geo-localization performance by improving both retrieval accuracy and metric localization references. Extensive experiments demonstrate that UnifyGeo significantly outperforms the state-of-the-arts in both task-isolated and task-associated settings. Remarkably, on the challenging VIGOR benchmark, which supports fine-grained localization evaluation, the 1-meter-level localization recall rate improves from 1.53\% to 39.64\% and from 0.43\% to 25.58\% under same-area and cross-area evaluations, respectively. Code will be made publicly available.
title A Unified Hierarchical Framework for Fine-grained Cross-view Geo-localization over Large-scale Scenarios
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.07622