VicenteVivan/geo-clip

This is an official PyTorch implementation of our NeurIPS 2023 paper "GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization"

45
/ 100
Emerging

This tool helps you pinpoint the exact geographical coordinates (latitude and longitude) of where a photo was taken, even if it doesn't have embedded GPS data. You feed it an image, and it outputs the most probable GPS locations along with their confidence scores. This is useful for researchers, photojournalists, or anyone needing to determine the origin of an image.

330 stars. No commits in the last 6 months.

Use this if you need to accurately geo-locate an image from anywhere in the world and identify its likely geographic coordinates.

Not ideal if you already have GPS data embedded in your images or if you only need general regional identification rather than precise coordinates.

image-geolocation geospatial-intelligence photo-analysis geographic-information-systems digital-forensics
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

330

Forks

39

Language

Python

License

MIT

Last pushed

Oct 05, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/VicenteVivan/geo-clip"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.