panpanfei / DPSR

Deep Plug-and-Play Super-Resolution for Arbitrary Blur Kernels (CVPR, 2019) (PyTorch)

Home Page:https://cszn.github.io/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

DPSR

Deep Plug-and-Play Super-Resolution for Arbitrary Blur Kernels (CVPR, 2019)

  • Related work: DPIR

Training and testing codes for the super-resolver prior (PyTorch)


The left is the blurry LR image. The right is the super-resolved image by DPSRGAN with scale factor 4.

Run demo_test_dpsr.py to produce the following results.


Super-resolved images of LR image chip.png by DPSR with scale factors 2, 3 and 4.

Run demo_test_dpsr_real.py to produce the following results.

LR

x2

x3

x4

Requirements and Dependencies

  • Spyder (Python 3.6)
  • PyTorch 0.4.1
  • Windows 10

Citation

@inproceedings{zhang2019deep,
  title={Deep Plug-and-Play Super-Resolution for Arbitrary Blur Kernels},
  author={Zhang, Kai and Zuo, Wangmeng and Zhang, Lei},
  booktitle={IEEE Conference on Computer Vision and Pattern Recognition},
  pages={1671--1681},
  year={2019}
}

About

Deep Plug-and-Play Super-Resolution for Arbitrary Blur Kernels (CVPR, 2019) (PyTorch)

https://cszn.github.io/


Languages

Language:Python 96.4%Language:MATLAB 3.5%Language:M 0.1%