ozgurkara99/ISNAS-DIP
ISNAS-DIP: Image Specific Neural Architecture Search for Deep Image Prior [CVPR 2022]
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.
Stars
31
Forks
5
Language
Jupyter Notebook
License
MIT
Category
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.
Higher-rated alternatives
CAREamics/careamics
A deep-learning library for denoising images using Noise2Void and friends (CARE, PN2V, HDN...
yu4u/noise2noise
An unofficial and partial Keras implementation of "Noise2Noise: Learning Image Restoration...
rgeirhos/texture-vs-shape
Pre-trained models, data, code & materials from the paper "ImageNet-trained CNNs are biased...
NICALab/SUPPORT
Accurate denoising of voltage imaging data through statistically unbiased prediction, Nature Methods.
jaewon-lee-b/lte
Local Texture Estimator for Implicit Representation Function, in CVPR 2022