Plonk
1 like
Introducing the first generative geolocation method based on diffusion and flow matching! We learn the relationship between visual content and location by denoising random locations conditionally to images.
Cost / License
- Free
- Open Source
EUPlatforms
- Python
- Hugging Face
- Online
Features
- AI-Powered
Tags
- diffusion-model
- photo-location
- ai-geolocation
- Generative AI
- geolocation
Plonk News & Activities
Highlights All activities
Recent activities
- niksavc liked Plonk
POX added Plonk as alternative to Overpass Turbo, ArcGIS, Plus Codes and CartoDB- POX added Plonk
Plonk information
Developed by
Nicolas Dufour Licensing
Open Source (MIT) and Free product.Alternatives
12 alternatives listedSupported Languages
- English
AlternativeTo Categories
AI Tools & Services, Travel & LocationGitHub repository
- 257 Stars
- 21 Forks
- 1 Open Issues
- Updated
No comments or reviews, maybe you want to be first?
Post comment/reviewWhat is Plonk?
Introducing the first generative geolocation method based on diffusion and flow matching! We learn the relationship between visual content and location by denoising random locations conditionally to images.
- New SOTA for visual geolocation on OpenStreetView-5M, YFCC-100M, and iNat-21
- Generate global probability density maps and quantify localizability
- Introduce the problem of probabilistic visual geolocation
Our model predicts location distributions for images from three major visual geolocation datasets: iNat-21 (wildlife), YFCC-100M (natural images), and OSV-5M (street-view). The model can handle varying levels of location ambiguity by outputting appropriate probability distributions.