ConGeo: Robust Cross-view Geo-localization across Ground View Variations

arXiv:2403.13965v1 Announce Type: new
Abstract: Cross-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 …

abstract aerial arxiv cs.cv diverse geo however image images localization pipelines query robust type view world