The idea of colorization is given a grayscale image as input, the model hallucinates a plausible, vibrant & realistic colorized version of the image.
About Colorization-v2
- The colorization-v2 model is one of the colorization group of models designed to perform image colorization.
- Model was trained on ImageNet dataset.
- Model consumes as input L-channel of LAB-image and give as output predict A- and B-channels of LAB-image.
About Colorization-siggraph
- The colorization-siggraph model is one of the colorization group of models designed to real-time user-guided image colorization.
- Model was trained on ImageNet dataset with synthetically generated user interaction.
- Model consumes as input L-channel of LAB-image and yields output predict A- and B-channels of LAB-image.
Check out colorization repository for more details.
This notebook demonstrates how to colorize images with OpenVINO using the Colorization model colorization-v2 or colorization-siggraph from Open Model Zoo based on the paper: Colorful Image Colorization.
If you have not installed all required dependencies, follow the Installation Guide.