CoreML Image Colorizer Models

This repository contains CoreML versions of the ECCV16Colorizer and SIGGraph17Colorizer models, originally implemented in PyTorch. These models can be used to colorize black and white images on iOS devices.

Models

ECCV16Colorizer.mlpackage: The main CoreML model for image colorization from 2016.
SIGGraph17Colorizer.mlpackage: The CoreML model for image colorization from 2017.

Description

These CoreML models are converted from the PyTorch implementation of the ECCV16Colorizer. They use the 'L' channel of an image in the Lab color space to predict the 'a' and 'b' color channels, effectively colorizing black and white images.

Usage

To use these models in your iOS app:

Download the desired .mlpackage file.
Add the model to your Xcode project.
Use CoreML framework to integrate the model into your app.

For a complete implementation example, check out the GitHub repository.

Model Input

Format: MLShapedArray
Shape: [1, 1, 512, 512]
Description: 'L' channel of the input image in Lab color space

Model Output

Format: MLShapedArray
Shape: [1, 2, 512, 512]
Description: Predicted 'a' and 'b' channels in Lab color space

Original Implementation

This CoreML model is based on the PyTorch implementation of ECCV16Colorizer. For more information about the original model and its implementation, please refer to the original repository.

iOS Demo App

For a complete iOS app showcasing this model in action, check out our GitHub repository.

Citation

If you use this model in your research or project, please cite the original work:

@inproceedings{zhang2016colorful,
  title={Colorful Image Colorization},
  author={Zhang, Richard and Isola, Phillip and Efros, Alexei A},
  booktitle={ECCV},
  year={2016}
}

Created by Sharan Thakur GitHub: https://github.com/c2p-cmd