Skip to content

Latest commit

 

History

History
43 lines (30 loc) · 1.36 KB

README.md

File metadata and controls

43 lines (30 loc) · 1.36 KB

DerainNet (TIP'2017)

Clearing the Skies: A Deep Network Architecture for Single-Image Rain Removal (TIP'2017)
@article{fu2017clearing,
  title={Clearing the skies: A deep network architecture for single-image rain removal},
  author={Fu, Xueyang and Huang, Jiabin and Ding, Xinghao and Liao, Yinghao and Paisley, John},
  journal={IEEE Transactions on Image Processing},
  volume={26},
  number={6},
  pages={2944--2956},
  year={2017},
  publisher={IEEE}
}

derainnet


Quantitative Result

The metrics are PSNR/SSIM. Both are evaluated on RGB channels.

Method Rain200L Rain200H Rain800 Rain1200 Rain1400
derainnet_c512 31.12/0.939 22.96/0.739 23.17/0.783 28.34/0.847 28.20/0.869

Pretrained models can be downloaded from here


Network Complexity

Input shape Flops Params
(3, 256, 256) 51.48GFlops 754.69k