Use of GAN approach in order to generate monte carlo noise applied on synthesis images

Jérôme BUISINE 714bc0055b Merge branch 'release/v0.0.2' 1 year ago
synthesis_images 6901223dae Update of data; Save and load option added 2 years ago
.gitignore a003b62672 Update of documentation 1 year ago
Dockerfile b89725ffd3 Add of gan for image synthesis 2 years ago
LICENSE a003b62672 Update of documentation 1 year ago
Makefile b89725ffd3 Add of gan for image synthesis 2 years ago
README.md a003b62672 Update of documentation 1 year ago
ganAtariImage.py b89725ffd3 Add of gan for image synthesis 2 years ago
ganSynthesisImage.py 70d4356303 try using 200 pixels images 2 years ago
ganSynthesisImage_100.py 51f1999d4f Add of gan for 100x100 images 2 years ago
ganSynthesisImage_200.py 6901223dae Update of data; Save and load option added 2 years ago
noise_gan.ipynb 51f1999d4f Add of gan for 100x100 images 2 years ago
prepare_data.py 6901223dae Update of data; Save and load option added 2 years ago
requirements.txt b89725ffd3 Add of gan for image synthesis 2 years ago
tensorboard.ipynb 51f1999d4f Add of gan for 100x100 images 2 years ago

README.md

Noise Generation

Description

Study of how to generate noise filter from monte carlo rendering in synthesis images using Generative Adversarial Network approach. The aim of this project is to reproduce monte carlo noise obtained during rendering.

How to use ?

pip install -r requirements.txt
python prepare_data.py
python ganSynthesisImage_200.py

Contributors

License

MIT