WooKyoungHan/ABCD

Official implementation of the CVPR'23 Paper "ABCD : Arbitrary Bitwise Coefficient for De-quantization"

35
/ 100
Emerging

This project helps image processing professionals restore the quality of images that have lost detail due to quantization, a common process that reduces file size by compressing color information. You provide a quantized image, and it outputs a de-quantized, higher-quality version, making it useful for digital artists, photographers, or anyone working with compressed image files.

No commits in the last 6 months.

Use this if you need to recover visual detail from images that have been aggressively compressed or have lost color depth due to quantization, and you want to restore them to a more visually accurate state.

Not ideal if your image quality issues stem from problems other than quantization, such as motion blur, noise, or poor original capture quality.

image-restoration digital-photography computer-graphics image-processing visual-content-creation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

28

Forks

4

Language

Python

License

BSD-3-Clause

Last pushed

Jun 01, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/WooKyoungHan/ABCD"

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