Accurate visual localization from aerial views is a fundamental problem with applications in mapping, large-area inspection, and search-and-rescue operations. In many scenarios, these systems require high-precision localization while operating with limited resources (e.g., no internet connection or GNSS/GPS support), making large image databases or heavy 3D models impractical. Surprisingly, little attention has been given to leveraging orthographic geodata as an alternative paradigm, which is lightweight and increasingly available through free releases by governmental authorities (e.g., the European Union).
To fill this gap, we propose OrthoLoC, the first large-scale dataset comprising 16,425 UAV images from Germany and the United States with multiple modalities. The dataset addresses domain shifts between UAV imagery and geospatial data. Its paired structure enables fair benchmarking of existing solutions by decoupling image retrieval from feature matching, allowing isolated evaluation of localization and calibration performance. Through comprehensive evaluation, we examine the impact of domain shifts, data resolutions, and covisibility on localization accuracy. Finally, we introduce a refinement technique called AdHoP, which can be integrated with any feature matcher, improving matching by up to 95% and reducing translation error by up to 63%.
OrthoLoC is a comprehensive UAV localization dataset that addresses key limitations in existing benchmarks. Our dataset comprises 16.4k real UAV images spanning 47 locations across 19 regions in Germany and the United States, captured in diverse environmental contexts including urban, suburban, industrial, rural, and highway scenes. Each sample provides a query image with precise ground-truth 6-DoF pose, camera intrinsics, and rich 3D scene representations: point maps, 3D keypoints, local meshes, and aligned 2.5D geodata rasters derived from multiple sources.
The OrthoLoC dataset is licensed under CC BY-NC-SA 4.0
Geodata used for augmenting the dataset to close the gap of cross-domain are issued from multiple open
geoportals in Europe which have the CC BY 4.0 license. Please consult the following list for the
specific license of the data used in this dataset:
Our dataset demonstrates precise alignment of geodata from diverse sources, including 3D photogrammetry reconstructions and open geoportal downloads. This crucial capability enables superior localization and calibration performance — a feature notably absent in datasets like AnyVisLoc.
@inproceedings{dhaouadi2025ortholoc,
title = {OrthoLoC: UAV 6-DoF Localization and Calibration Using Orthographic Geodata},
author = {Dhaouadi, Oussema and Marin Riccardo and Meier, Johannes and Kaiser, Jacques and Cremers, Daniel},
booktitle = {(under review)},
year = {2025},
}