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

Jérôme BUISINE 714bc0055b Merge branch 'release/v0.0.2' 5 лет назад
synthesis_images 6901223dae Update of data; Save and load option added 5 лет назад
.gitignore a003b62672 Update of documentation 5 лет назад
Dockerfile b89725ffd3 Add of gan for image synthesis 6 лет назад
LICENSE a003b62672 Update of documentation 5 лет назад
Makefile b89725ffd3 Add of gan for image synthesis 6 лет назад
README.md a003b62672 Update of documentation 5 лет назад
ganAtariImage.py b89725ffd3 Add of gan for image synthesis 6 лет назад
ganSynthesisImage.py 70d4356303 try using 200 pixels images 5 лет назад
ganSynthesisImage_100.py 51f1999d4f Add of gan for 100x100 images 5 лет назад
ganSynthesisImage_200.py 6901223dae Update of data; Save and load option added 5 лет назад
noise_gan.ipynb 51f1999d4f Add of gan for 100x100 images 5 лет назад
prepare_data.py 6901223dae Update of data; Save and load option added 5 лет назад
requirements.txt b89725ffd3 Add of gan for image synthesis 6 лет назад
tensorboard.ipynb 51f1999d4f Add of gan for 100x100 images 5 лет назад

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