yu4u/noise2noise

An unofficial and partial Keras implementation of "Noise2Noise: Learning Image Restoration without Clean Data"

51
/ 100
Established

This tool helps improve the quality of images by removing various types of noise, such as static, text, or impulse artifacts. It takes noisy images as input and produces clearer, denoised versions, even without requiring perfectly clean reference images for training. It's designed for researchers and practitioners working with image processing and computer vision applications who need to clean up imperfect image data.

1,092 stars. No commits in the last 6 months.

Use this if you need to remove noise from images and traditional denoising methods are difficult to apply due to the lack of clean, pristine reference images for training.

Not ideal if you already have access to a large dataset of perfectly clean images paired with their noisy counterparts, as standard denoising methods might offer superior results.

image-denoising image-enhancement computer-vision image-restoration digital-photography
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

1,092

Forks

235

Language

Python

License

MIT

Last pushed

Aug 12, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/yu4u/noise2noise"

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