geolocal/StreetCLIP · Hugging Face
alive
HTTP 200
Last checked: 2026-03-02T21:38
Description
StreetCLIP is an AI model trained on 1.1 million street-level images that can geolocate photos to specific countries, regions, or cities using zero-shot learning, and can be applied to downstream tasks like analyzing urban infrastructure, vegetation, and building conditions. The model achieves state-of-the-art performance on image geolocalization benchmarks and is available on Hugging Face for research and applications with geographic or street-level scene understanding requirements.