1. CV-Cities: Advancing Cross-View Geo-Localization in Global Cities
- Author
-
Gaoshuang Huang, Yang Zhou, Luying Zhao, and Wenjian Gan
- Subjects
Cross-view geo-localization (CVGL) ,dataset ,global cities ,image retrieval ,visual place recognition ,Ocean engineering ,TC1501-1800 ,Geophysics. Cosmic physics ,QC801-809 - Abstract
Cross-view geo-localization (CVGL), which involves matching and retrieving satellite images to determine the geographic location of a ground image, is crucial in GNSS-constrained scenarios. However, this task faces significant challenges due to substantial viewpoint discrepancies, the complexity of localization scenarios, and the need for global localization. To address these issues, we propose a novel CVGL framework that integrates the vision foundational model DINOv2 with an advanced feature mixer. Our framework introduces the symmetric InfoNCE loss and incorporates near-neighbor sampling and dynamic similarity sampling strategies, significantly enhancing localization accuracy. Experimental results show that our framework surpasses existing methods across multiple public and self-built datasets. To further improve global-scale performance, we have developed CV-Cities, a novel dataset for global CVGL. CV-Cities includes 223 736 ground-satellite image pairs with geolocation data, spanning sixteen cities across six continents and covering a wide range of complex scenarios, providing a challenging benchmark for CVGL. The framework trained with CV-Cities demonstrates high localization accuracy in various test cities, highlighting its strong globalization and generalization capabilities.
- Published
- 2025
- Full Text
- View/download PDF