Skip to content

Implemented Image De-raining Using a Conditional Generative Adversarial Network using Keras

License

Notifications You must be signed in to change notification settings

akshatsonic/Single-Image-De-Raining-Keras

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

11 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Single-Image-De-Raining-Keras

Implemented Image De-raining Using a Conditional Generative Adversarial Network using Keras

[Paper Link]

Severe weather conditions such as rain and snow adversely affect the visual quality of images captured under such conditions thus rendering them useless for further usage and sharing. In addition, such degraded images drastically affect performance of vision systems. Hence, it is important to solve the problem of single image de-raining/de-snowing.

In this project I implemented the Paper using Keras.

It is kept in mind that the de-rained result should be indistinguishable from its corresponding clear image.

@article{zhang2017image,		
  title={Image De-raining Using a Conditional Generative Adversarial Network},
  author={Zhang, He and Sindagi, Vishwanath and Patel, Vishal M},
  journal={arXiv preprint arXiv:1701.05957},
  year={2017}
} 

*Make sure to change scipy version to 1.1.0

Download the dataset from (https://drive.google.com/open?id=0Bw2e6Q0nQQvGbi1xV1Yxd09rY2s)

##Acknowledgment##

Code borrows heavily from [Pix2Pix Peceptual Loss] and [Pix2Pix]. Thanks for the sharing.

About

Implemented Image De-raining Using a Conditional Generative Adversarial Network using Keras

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%