References & Citations
Computer Science > Computer Vision and Pattern Recognition
Title: OpenStreetView-5M: The Many Roads to Global Visual Geolocation
(Submitted on 29 Apr 2024)
Abstract: Determining the location of an image anywhere on Earth is a complex visual task, which makes it particularly relevant for evaluating computer vision algorithms. Yet, the absence of standard, large-scale, open-access datasets with reliably localizable images has limited its potential. To address this issue, we introduce OpenStreetView-5M, a large-scale, open-access dataset comprising over 5.1 million geo-referenced street view images, covering 225 countries and territories. In contrast to existing benchmarks, we enforce a strict train/test separation, allowing us to evaluate the relevance of learned geographical features beyond mere memorization. To demonstrate the utility of our dataset, we conduct an extensive benchmark of various state-of-the-art image encoders, spatial representations, and training strategies. All associated codes and models can be found at this https URL
Submission history
From: Guillaume Astruc [view email][v1] Mon, 29 Apr 2024 17:06:44 GMT (43547kb,D)
Link back to: arXiv, form interface, contact.