JK-the-Ko/Self2SelfPlus
[arXiv Preprint] Official PyTorch Implementation of "Self2Self+: Single-Image Denoising with Self-Supervised Learning and Image Quality Assessment Loss"
This project helps image processing specialists and researchers remove unwanted noise from digital images. It takes a single noisy image as input and produces a cleaner, denoised version. This is particularly useful for anyone working with photos that suffer from imperfections due to low-light conditions, sensor limitations, or other sources of degradation.
No commits in the last 6 months.
Use this if you need to clean up individual noisy images without requiring a separate 'perfect' clean version for comparison or an extensive dataset of noisy-clean pairs.
Not ideal if you prefer a solution that comes with pre-trained models, as this method trains a denoising network specifically for each image.
Stars
17
Forks
1
Language
Python
License
BSD-3-Clause
Category
Last pushed
Sep 07, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/JK-the-Ko/Self2SelfPlus"
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...