egenioussBench: A New Dataset for Geospatial Visual Localisation

TL;DR

egenioussBench introduces a scalable, city-scale geospatial visual localisation dataset with diverse images, precise ground truth, and a comprehensive evaluation framework to advance large-scale localisation methods.

Contribution

It provides a novel, scalable dataset and benchmark for geospatial visual localisation using realistic city-scale data and a new evaluation protocol.

Findings

Benchmark includes 42 non-co-visible images with withheld ground truth.

Validation set contains 412 sequential images with pose annotations.

Evaluation framework supports fair comparison across different localisation methods.

Abstract

We present egenioussBench, a visual localisation benchmark built on geospatial reference data: a city-scale airborne 3D mesh and a CityGML LoD2 model. This pairing reflects deployable mapping assets and supports true scalability beyond traditional SfM-based approaches. The query data comprise smartphone images with centimetre-accurate, map-independent ground truth obtained via PPK and GCP/CP-aided adjustment. From 2,709 images, we derive a non-co-visible subset by estimating the full co-visibility matrix from rendered depth and selecting a maximum independent set; the released data include a test split of 42 non-co-visible images with withheld ground truth and a validation split of 412 sequential images with poses, e.g. for training of pose regressors and self-validation. The benchmark features a public leaderboard evaluated with binning metrics at multiple pose-error thresholds alongside global statistics (median, RMSE, outlier ratio), ensuring fair, like-for-like comparison across mesh- and LoD2-based methods. Together, these design choices expose realistic cross-view and cross-domain challenges while providing a rigorous, scalable path for advancing large-scale visual localisation. We make the evaluation code and data availeable at https://github.com/fratopa/egenioussBench and https://www.egeniouss.eu/