billpsomas/rscir

Official PyTorch implementation and benchmark dataset for IGARSS 2024 ORAL paper: "Composed Image Retrieval for Remote Sensing"

31
/ 100
Emerging

This project helps remote sensing professionals efficiently search vast archives of satellite and aerial imagery. Instead of just using a sample image or a text description, you can combine both – an image that looks generally right, plus text to refine details like color, density, or shape. This allows earth observation scientists, urban planners, and environmental analysts to find very specific images that meet complex criteria.

No commits in the last 6 months.

Use this if you need to find specific remote sensing images by combining both visual examples and detailed text descriptions to pinpoint exact features.

Not ideal if your image retrieval needs are straightforward and can be met by searching with only an image or only a text description.

remote-sensing earth-observation satellite-imagery geospatial-analysis image-archive-management
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

82

Forks

3

Language

Python

License

Apache-2.0

Last pushed

Dec 21, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/billpsomas/rscir"

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