Use of an autoencoding model for denoising synthetic images

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

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