tangkai-RS/DreamCD

[JAG 2026] DreamCD: A change-label-free framework for change detection via a weakly conditional semantic diffusion model in optical VHR imagery

27
/ 100
Experimental

This project helps environmental analysts, urban planners, and disaster responders identify changes in very high-resolution satellite imagery over time, without needing pre-labeled examples of what 'change' looks like. You provide two satellite images of the same area taken at different times, and it outputs a new 'post-event' image that highlights the detected changes, along with a mask clearly showing where changes occurred. This is useful for anyone monitoring land use, deforestation, or damage after natural disasters.

Use this if you need to detect changes in satellite or aerial imagery but lack extensive, manually labeled datasets of 'changed' and 'unchanged' areas.

Not ideal if you require real-time change detection for streaming data or if you primarily work with lower-resolution imagery.

remote-sensing geospatial-analysis land-cover-monitoring disaster-assessment urban-development
No License No Package No Dependents
Maintenance 10 / 25
Adoption 6 / 25
Maturity 7 / 25
Community 4 / 25

How are scores calculated?

Stars

22

Forks

1

Language

Python

License

Last pushed

Jan 30, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/tangkai-RS/DreamCD"

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