Sākums Izpētīt Palīdzība
Pierakstīties
Prise3D
/
Thesis-NoiseGeneration
5
0
Atdalīts 0
Faili Problēmas 0 Izmaiņu pieprasījumi 0 Vikivietne

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

Atzars: develop
Atzari Tagi
Thesis-Noise...
ZIP TAR.GZ
Jérôme BUISINE 17dce75e75 Merge tag 'v0.0.2' into develop 5 gadi atpakaļ
synthesis_images 6901223dae Update of data; Save and load option added 5 gadi atpakaļ
.gitignore a003b62672 Update of documentation 5 gadi atpakaļ
Dockerfile b89725ffd3 Add of gan for image synthesis 5 gadi atpakaļ
LICENSE a003b62672 Update of documentation 5 gadi atpakaļ
Makefile b89725ffd3 Add of gan for image synthesis 5 gadi atpakaļ
README.md a003b62672 Update of documentation 5 gadi atpakaļ
ganAtariImage.py b89725ffd3 Add of gan for image synthesis 5 gadi atpakaļ
ganSynthesisImage.py 70d4356303 try using 200 pixels images 5 gadi atpakaļ
ganSynthesisImage_100.py 51f1999d4f Add of gan for 100x100 images 5 gadi atpakaļ
ganSynthesisImage_200.py 6901223dae Update of data; Save and load option added 5 gadi atpakaļ
noise_gan.ipynb 51f1999d4f Add of gan for 100x100 images 5 gadi atpakaļ
prepare_data.py 6901223dae Update of data; Save and load option added 5 gadi atpakaļ
requirements.txt b89725ffd3 Add of gan for image synthesis 5 gadi atpakaļ
tensorboard.ipynb 51f1999d4f Add of gan for 100x100 images 5 gadi atpakaļ

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