jaychempan/EarthSynth

Official Code for “EarthSynth: Generating Informative Earth Observation with Diffusion Models”

33
/ 100
Emerging

This project helps remote sensing analysts and researchers overcome the challenge of limited labeled satellite imagery for training their interpretation models. It takes descriptions of ground features and generates synthetic, high-quality satellite images and corresponding mask data. This allows users to create diverse training datasets, improving the performance of tasks like identifying roads, vehicles, or specific land covers in real-world satellite imagery.

Use this if you need to generate realistic, labeled satellite imagery for training or testing remote sensing models, especially when real-world labeled data is scarce.

Not ideal if you primarily need to analyze existing satellite data without generating new synthetic images.

satellite-imagery remote-sensing geospatial-analysis image-generation environmental-monitoring
No Package No Dependents
Maintenance 6 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 3 / 25

How are scores calculated?

Stars

54

Forks

1

Language

Python

License

MIT

Last pushed

Oct 30, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/jaychempan/EarthSynth"

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