YupeiLin2388/Diff-Mosaic

[TGRS 2024]Diff-Mosaic: Augmenting Realistic Representations in Infrared Small Target Detection via Diffusion Prior

24
/ 100
Experimental

This project helps improve the detection of very small objects in infrared images. It takes your existing infrared imagery, especially those with tiny, hard-to-see targets, and generates augmented, more realistic versions of these images. The output is a set of enhanced infrared images that can be used to train better target detection systems, which is useful for surveillance, search and rescue, or military applications.

No commits in the last 6 months.

Use this if you need to detect extremely small targets in infrared imagery and your current detection models struggle due to a lack of diverse or challenging training data.

Not ideal if you are working with visible light images or if your primary goal is general object detection rather than specialized small target identification in infrared.

infrared-imaging target-detection surveillance image-enhancement thermal-imagery
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

20

Forks

Language

Python

License

MIT

Last pushed

Sep 18, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/YupeiLin2388/Diff-Mosaic"

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