egenioussBench dataset advances geospatial visual localization benchmarks

Researchers have introduced egenioussBench, a new dataset designed for geospatial visual localization. This benchmark utilizes a city-scale 3D mesh and a CityGML LoD2 model, reflecting real-world mapping assets for scalable localization. It includes smartphone images with precise ground truth and a test split of non-co-visible images to evaluate methods rigorously. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT Introduces a new benchmark for advancing large-scale visual localization techniques.

RANK_REASON This is a research paper introducing a new dataset and benchmark for visual localization. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• egenioussBench
• CityGML
• Francesco Vultaggio
• arXiv

• paper
• other