WooKyoungHan/ABCD
Official implementation of the CVPR'23 Paper "ABCD : Arbitrary Bitwise Coefficient for De-quantization"
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.
Stars
28
Forks
4
Language
Python
License
BSD-3-Clause
Category
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.
Higher-rated alternatives
zhangyi-3/IDR
Self-Supervised Image Denoising via Iterative Data Refinement (CVPR2022)
yinboc/liif
Learning Continuous Image Representation with Local Implicit Image Function, in CVPR 2021 (Oral)
XingangPan/deep-generative-prior
Code for deep generative prior (ECCV2020 oral)
mv-lab/swin2sr
[ECCV] Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration. ...
eliahuhorwitz/DeepSIM
Official PyTorch implementation of the paper: "DeepSIM: Image Shape Manipulation from a Single...