Skip to content

Image Restoration & Enhancement using Deep Learning (Graduation Project)

Notifications You must be signed in to change notification settings

Mahmoud810/ImageRestorationAndEnhancement

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

14 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Graduation project for image restoration, enhancement & colorization.

Installation

Run setup.sh to download weights & models & stuff.

Running

Run main.py to generate results. Input directory is sample_images, but you can change that (see run in main.py).

Output

According to RunMode and whether colorize is set, output is either <output-dir>/face_restore or <output-dir>/quality_enh/restored_image or <output-dir>/colorization (also see run in main.py).

Sample resulst

TODO

  • Supplant out-of-the-box face restoration in scratched photos with GPEN's face inpainting. Not sure if it'd work though. We'd have to blend in the restored face to the result of running vanilla scratch restoration.

Credits

Old photo restoration by deep latent space translation

GPEN

DeOldify

About

Image Restoration & Enhancement using Deep Learning (Graduation Project)

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 97.1%
  • Cuda 2.4%
  • Other 0.5%