gmberton/deep-visual-geo-localization-benchmark

Official code for CVPR 2022 (Oral) paper "Deep Visual Geo-localization Benchmark"

42
/ 100
Emerging

This tool helps researchers and engineers evaluate and compare different visual geo-localization (VG) techniques. You input a collection of geographically tagged images (like from a self-driving car dataset) and it outputs performance metrics (like recall) for various VG methods. It's designed for anyone working on improving the accuracy of location recognition using visual data.

251 stars. No commits in the last 6 months.

Use this if you need to rigorously test and benchmark different computer vision models for their ability to accurately determine a location from images.

Not ideal if you're looking for a ready-to-use application for everyday image-based navigation or real-time location services without extensive setup.

visual-geo-localization robotics-navigation image-retrieval location-recognition computer-vision-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

251

Forks

31

Language

Python

License

MIT

Last pushed

Jan 29, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/gmberton/deep-visual-geo-localization-benchmark"

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