Use of GAN approach in order to generate monte carlo noise applied on synthesis images
Jérôme BUISINE 17dce75e75 Merge tag 'v0.0.2' into develop | 5 lat temu | |
---|---|---|
synthesis_images | 5 lat temu | |
.gitignore | 5 lat temu | |
Dockerfile | 6 lat temu | |
LICENSE | 5 lat temu | |
Makefile | 6 lat temu | |
README.md | 5 lat temu | |
ganAtariImage.py | 6 lat temu | |
ganSynthesisImage.py | 6 lat temu | |
ganSynthesisImage_100.py | 5 lat temu | |
ganSynthesisImage_200.py | 5 lat temu | |
noise_gan.ipynb | 5 lat temu | |
prepare_data.py | 5 lat temu | |
requirements.txt | 6 lat temu | |
tensorboard.ipynb | 5 lat temu |
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