Dual Attention-guided Detail and Structure Information Fusion Network for Image Dehazing

This package contains dehazing model and the test code which is associated with the following paper:

Dual Attention-guided Detail and Structure Information Fusion Network for Image Dehazing(双注意力引导的细节和结构信息融合图像去雾网络)

Usage of this code is free for research purposes only.

Thank you.

Requirements:

CUDA  10.0
Python  3.7.7
Pytorch  1.5.0
torchvision  0.6.0
numpy  1.17.4

Get Started

1.Install:

download the code
git clone https://github.com/lhf12278/DS-Net.git
cd DS-Net

2.Test

Put your test images into "data/test/SOTS/". Run test.py using default hyper-parameter settings.

Contact:

Don't hesitate to contact me if you meet any problems when using this code.

Gao Jirui
Faculty of Information Engineering and Automation
Kunming University of Science and Technology                                                           
Email: 2945266153@qq.com

Acknowledgements

Our code is based on : https://proteus1991.github.io/GridDehazeNet,https://github.com/zhilin007/FFA-Net.