Mi, LiXu, ChangCastillo-Navarro, JavieraMontariol, SyrielleYang, WenBosselut, AntoineTuia, Devis2025-01-262025-01-262025-03-182025-01-252024-12-0510.1007/978-3-031-72630-9_132-s2.0-85212921346https://infoscience.epfl.ch/handle/20.500.14299/245014Cross-view geo-localization aims at localizing a ground-level query image by matching it to its corresponding geo-referenced aerial view. In real-world scenarios, the task requires accommodating diverse ground images captured by users with varying orientations and reduced field of views (FoVs). However, existing learning pipelines are orientation-specific or FoV-specific, demanding separate model training for different ground view variations. Such models heavily depend on the North-aligned spatial correspondence and predefined FoVs in the training data, compromising their robustness across different settings. To tackle this challenge, we propose ConGeo, a single- and cross-view Contrastive method for Geo-localization: it enhances robustness and consistency in feature representations to improve a model’s invariance to orientation and its resilience to FoV variations, by enforcing proximity between ground view variations of the same location. As a generic learning objective for cross-view geo-localization, when integrated into state-of-the-art pipelines, ConGeo significantly boosts the performance of three base models on four geo-localization benchmarks for diverse ground view variations and outperforms competing methods that train separate models for each ground view variation.enfalsetext::conference output::conference proceedings::conference paper