ozgurkara99/ISNAS-DIP

ISNAS-DIP: Image Specific Neural Architecture Search for Deep Image Prior [CVPR 2022]

36
/ 100
Emerging

This project helps researchers and engineers improve the quality of degraded images in fields like medical imaging or remote sensing. It takes a noisy, blurry, or incomplete image and identifies the most effective neural network architecture specifically for that single image. The output is a significantly enhanced image, free from common defects, tailored to its unique characteristics. This is for image processing specialists who need optimal restoration for individual images.

No commits in the last 6 months.

Use this if you need to restore individual degraded images (denoising, inpainting, super-resolution) and want to automatically find the best-performing neural network architecture tailored to each specific image.

Not ideal if you need a general image restoration solution that applies the same network architecture across an entire dataset without individual image optimization.

image-restoration medical-imaging remote-sensing image-denoising image-enhancement
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

31

Forks

5

Language

Jupyter Notebook

License

MIT

Last pushed

Aug 15, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ozgurkara99/ISNAS-DIP"

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