Cross-view geo-localization (CVGL) aims to match images of the same location captured from drastically different viewpoints. Despite recent progress, existing methods still face two key challenges: (1) achieving robustness under severe appearance variations induced by diverse UAV orientations and fields of view, which hinders cross-domain generalization, and (2) establishing reliable correspondences that capture both global scene-level semantics and fine-grained local details. In this paper, we propose EGS, a novel CVGL framework designed to enhance cross-domain generalization. Specifically, we introduce an E(2)-Steerable CNN encoder to extract stable and reliable features under rotation and viewpoint shifts. Furthermore, we construct a graph with a virtual super-node that connects to all local nodes, enabling global semantics to be aggregated and redistributed to local regions, thereby enforcing global-local consistency. Extensive experiments on the University-1652 and SUES-200 benchmarks demonstrate that EGS consistently achieves substantial performance gains and establishes a new state of the art in cross-domain CVGL.
@article{arxiv.2509.20684,
title = {Enhancing Cross-View Geo-Localization Generalization via Global-Local Consistency and Geometric Equivariance},
author = {Xiaowei Wang and Di Wang and Ke Li and Yifeng Wang and Chengjian Wang and Libin Sun and Zhihong Wu and Yiming Zhang and Quan Wang},
journal= {arXiv preprint arXiv:2509.20684},
year = {2025}
}