| Paper | Code | Street level (1 km) | City level (25 km) | Region level (200 km) | Country level (750 km) | Continent level (2500 km) | Training Images | Median Error (km) | ModelName | ReleaseDate |
|---|---|---|---|---|---|---|---|---|---|---|
| GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization | ✓ Link | 11.6 | 22.2 | 36.7 | 57.5 | 76.0 | 4.7M | GeoCLIP | 2023-09-27 | |
| PIGEON: Predicting Image Geolocations | ✓ Link | 10.5 | 25.8 | 42.7 | 63.2 | 79.0 | 4.5M | 333.3 | PIGEOTTO | 2023-07-11 |
| Where We Are and What We're Looking At: Query Based Worldwide Image Geo-localization Using Hierarchies and Scenes | 10.1 | 23.9 | 34.1 | 49.6 | 69.0 | 4.7M | GeoDecoder | 2023-03-07 | ||
| Where in the World is this Image? Transformer-based Geo-localization in the Wild | ✓ Link | 7.2 | 17.8 | 28.0 | 41.3 | 60.6 | 4.7M | Translocator | 2022-04-29 | |
| Geolocation Estimation of Photos using a Hierarchical Model and Scene Classification | ✓ Link | 5.3 | 12.3 | 19.0 | 31.9 | 50.7 | 4.7M | ISNs (M, f*, S3) | 2018-09-01 | |
| PlaNet - Photo Geolocation with Convolutional Neural Networks | ✓ Link | 4.4 | 11.0 | 16.9 | 28.5 | 47.7 | 30.3M | PlaNet | 2016-02-17 |