Use of an autoencoding model for denoising synthetic images

Jérôme BUISINE b5efdd2af6 Update of ignore files from project 5 years ago
modules bcc604e079 First model commit 5 years ago
.gitignore b5efdd2af6 Update of ignore files from project 5 years ago
LICENSE bcc604e079 First model commit 5 years ago
README.md 19b3967aa2 Update of model architecture 5 years ago
dataset 19b3967aa2 Update of model architecture 5 years ago
generate_dataset.py 19b3967aa2 Update of model architecture 5 years ago
generate_reconstructed_data.py bcc604e079 First model commit 5 years ago
image_denoising.py 19b3967aa2 Update of model architecture 5 years ago
transformation_functions.py 19b3967aa2 Update of model architecture 5 years ago

README.md

Denoising with autoencoder

Description

Utilisation d'un autoencoder pour apprendre statistiquement comment il est possible de générer une image de synthèse.

Input :

  • Noisy image
  • Z-buffer
  • Normal card

or other information...

Output :

  • Reference image

How to use ?

Autoencoder keras documentation

Detailed later...

License

The MIT license