Nithin-GK/AT-DDPM

[WACV '23] AT-DDPM: Restoring Faces degraded by Atmospheric Turbulence using Denoising Diffusion Probabilistic Models

32
/ 100
Emerging

This project helps restore facial images captured by long-range cameras that have been blurred and distorted by atmospheric turbulence. It takes a blurry, turbulent face image as input and outputs a clearer, reconstructed facial image with improved detail. This would be used by analysts or operators who rely on long-distance visual surveillance, security, or reconnaissance systems to identify individuals.

No commits in the last 6 months.

Use this if you need to recover identifiable facial features from images severely degraded by environmental factors like atmospheric turbulence.

Not ideal if your image degradation is due to factors other than atmospheric turbulence, such as low light, motion blur from camera shake, or poor focus.

long-range imaging facial recognition surveillance footage analysis image restoration security imaging
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

28

Forks

3

Language

Python

License

Apache-2.0

Last pushed

Jun 23, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Nithin-GK/AT-DDPM"

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