Skip to content

san-santra/CVPR2018_Dehazing

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

78bc2b7 · Sep 8, 2022

History

16 Commits
Apr 12, 2018
Apr 15, 2019
Apr 15, 2019
Apr 15, 2019
Jan 3, 2019

Repository files navigation

Code of the paper "Image Dehazing by Joint Estimation of Transmittance and Airlight using Bi-Directional Consistency Loss Minimized FCN"

Project Page

Input Dehzed
input dehazed

Dependency

  • For Running
    • Python 2
    • keras
    • scipy
    • numpy
    • scikit-image
    • matplotlib

Running

$ cd src/
$ python main.py  <hazy_image_dir>   <output_dir>

This runs the code in the supplied images.

$python main.py  ../data/hazy_img/ ../data/out/

Files

├── data
│   ├── hazy_img
│   │   └── lawn1_input.png
│   └── out
│       ├── ADelhi_Smog-PTI.jpg
│       ├── Delhi_Smog-PTI.jpg
│       └── TDelhi_Smog-PTI.jpg
├── models
│   └── model_weights.h5                   # Trained model
├── Readme.md
└── src
    ├── gf.py                              # guided filter
    ├── main_file.py
    ├── main.py                            # main file
    └── model.py                           # model

Publication

Ranjan Mondal, Sanchayan Santra and Bhabatosh Chanda. "Image Dehazing by Joint Estimation of Transmittance and Airlight using Bi-Directional Consistency Loss Minimized FCN" Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshop. 2018, pp-920-928.

BibTeX:

@inproceedings{mondal2018image,
  title={Image Dehazing by Joint Estimation of Transmittance and Airlight using Bi-Directional Consistency Loss Minimized FCN},
  author={Mondal, Ranjan and Santra, Sanchayan and Chanda, Bhabatosh},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops},
  pages={920--928},
  year={2018}
}

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%