Home Verkennen Help
Inloggen
Prise3D
/
Thesis-NoiseGeneration
5
0
Vork 0
Bestanden Issues 0 Pull-aanvragen 0 Wiki

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

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

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