This is the official PyTorch implementation of DW-GAN.
Our work is ranked 1st on NTIRE 2021 NonHomogeneous Dehazing Challenge (CVPR Workshop 2021).

See more details in [report] , [paper], [certificates]

• Ubuntu: 18.04

• CUDA Version: 11.0

• Python 3.8

• torch==1.6.0
• torchvision==0.7.0
• NVIDIA GPU and CUDA

1. Download ImageNet pretrained weights and Dehaze weights and place into the folder ./weights.
2. Download the NH-HAZE and NH-HAZE2 (only image pairs 1-25) dataset.

For inference, run following commands. Please check the test hazy image path (test.py line 12) and the output path (test.py line 13) .

python test.py

Results on NTIRE 2021 NonHomogeneous Dehazing Challenge validation images:

Results on NTIRE 2021 NonHomogeneous Dehazing Challenge testing images:

We thank the authors of Res2Net, MWCNN, and KTDN. Part of our code is built upon their modules.

If our work helps your research, please consider to cite our paper:

@InProceedings{Fu_2021_CVPR,
    author    = {Fu, Minghan and Liu, Huan and Yu, Yankun and Chen, Jun and Wang, Keyan},
    title     = {DW-GAN: A Discrete Wavelet Transform GAN for NonHomogeneous Dehazing},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
    month     = {June},
    year      = {2021},
    pages     = {203-212}
}