Invertible Grayscale

We run this code under TensorFlow 1.6 on Ubuntu16.04 with python pakage IPL installed.

Network Architecture

TensorFlow Implementation of our paper "Invertible Grayscale" accepted to SIGGRAPH ASIA 2018.

Results

Preparation

• You can use any color image set as the training data of the network, as it is a self-supervised learning scheme.
• The patch size is set to 256x256 in the model.py (you may change it to any other size as you like).
• Download the pretrained VGG19 model in here.

Run

• Set your image folders and hyperparameters in main.py.

• Start training.

line294: parser.add_argument('--mode', type=str, default='train', help='train, test')

python3 main.py

• Start evaluation. (access pretrained model)

line 294: parser.add_argument('--mode', type=str, default='test', help='train, test')

python3 main.py 

Copyright and License

You are granted with the license for both academic and commercial usages.