/UnpairedSR

This is an offical implementation of the CVPR2022's paper [Learning the Degradation Distribution for Blind Image Super-Resolution](https://arxiv.org/abs/2203.04962)

Primary LanguagePython

This is an offical implementation of the CVPR2022's paper Learning the Degradation Distribution for Blind Image Super-Resolution. This repo also contains the implementations of many other blind SR methods in config, including CinGAN, CycleSR, DSGAN-SR, etc.

If you find this repo useful for your work, please cite our paper:

@inproceedings{PDMSR,
  title={Learning the Degradation Distribution for Blind Image Super-Resolution},
  author={Zhengxiong Luo and Yan Huang and and Shang Li and Liang Wang and Tieniu Tan},
  booktitle={CVPR},
  year={2022}
}

The codes are built on the basis of BasicSR.

Dependences

  1. lpips (pip install --user lpips)
  2. matlab (to support the evaluation of NIQE). The details about installing a matlab API for python can refer to here

Datasets

The datasets in NTIRE2017 and NTIRE2018 can be downloaded from here. The datasets in NTIRE2020 can be downloaded from the competition site.

Start up

We provide the checkpoints in in Google drive and BaiduYun(password: ovmw). Please download them into the checkpoints directoty. To get a quick start:

cd codes/config/PDM-SR/
python3 inference.py --opt options/test/2020Track2.yml