This code is made publicly for research use only. 
It may be modified and redistributed under the terms of the GNU General Public License.
Please cite the paper and source code if you use it in your work.

@inproceedings{zhang2017towards,
title={Towards simulating foggy and hazy images and evaluating their authenticity},
author={Zhang, Ning and Zhang, Lin and Cheng, Zaixi},
booktitle={International Conference on Neural Information Processing},
pages={405--415},
year={2017},
organization={Springer}
}

This code has been tested in Windows10-64bit with Python3.4 installed.  
1. clone this project and put all the files in the same folder
2. folder structure:

      FoHIS/const.py  # define const
            fog.py  # main
            parameter.py # all parameters used in simulating fog/haze are defined here.
            tool_kit.py # some useful functions
            
      AuthESI/compute_aggd.py
              compute_authenticity.py  # main
              guided_filter.py  # some functions
              prisparam_16_hazeandfog.mat  # pre-trained model
              
      img/img.jpg  # RGB image
          imgd.jpg  # depth image
          result.jpg  # simulation
          
3. To simulate fog/haze effects:
    run python FoHIS/fog.py, the output 'result.jpg' will be saved in ../img/
      
4. To evaluate the authenticity:
    run python compute_authenticity.py to evaluate 'result.jpg' in ../img/