KDSR
This project is the official implementation of 'Knowledge Distillation based Degradation Estimation for Blind Super-Resolution', ICLR2023
Knowledge Distillation based Degradation Estimation for Blind Super-Resolution [Paper] [Project]
We provide Pretrained Models for KDSR-classic (for classic degradation models) and KDSR-GAN (for Real-world SR)
Dependencies and Installation
- Python >= 3.8 (Recommend to use Anaconda or Miniconda)
- PyTorch >= 1.10
Installation
-
Clone repo
git clone git@github.com:Zj-BinXia/KDSR.git
-
If you want to train or test KDSR-GAN (ie, Real-world SR, trained with the same degradation model as Real-ESRGAN)
cd KDSR-GAN
-
If you want to train or test KDSR-classic (ie, classic degradation models, trained with the isotropic Gaussian Blur or anisotropic Gaussian blur and noises)
cd KDSR-classic
More details please see the README in folder of KDSR-GAN and KDSR-classic
BibTeX
@InProceedings{xia2022knowledge,
title={Knowledge Distillation based Degradation Estimation for Blind Super-Resolution},
author={Xia, Bin and Zhang, Yulun and Wang, Yitong and Tian, Yapeng and Yang, Wenming and Timofte, Radu and Van Gool, Luc},
journal={ICLR},
year={2023}
}
📧 Contact
If you have any question, please email zjbinxia@gmail.com
.