Use of GAN approach in order to generate monte carlo noise applied on synthesis images
Jérôme BUISINE f18f368e30 Merge branch 'release/v0.0.2' | il y a 4 ans | |
---|---|---|
synthesis_images | il y a 5 ans | |
.gitignore | il y a 4 ans | |
Dockerfile | il y a 5 ans | |
LICENSE | il y a 4 ans | |
Makefile | il y a 5 ans | |
README.md | il y a 4 ans | |
ganAtariImage.py | il y a 5 ans | |
ganSynthesisImage.py | il y a 5 ans | |
ganSynthesisImage_100.py | il y a 5 ans | |
ganSynthesisImage_200.py | il y a 5 ans | |
noise_gan.ipynb | il y a 5 ans | |
prepare_data.py | il y a 5 ans | |
requirements.txt | il y a 5 ans | |
tensorboard.ipynb | il y a 5 ans |
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.
pip install -r requirements.txt
python prepare_data.py
python ganSynthesisImage_200.py