# Colorization 

Automatic colorization of grayscale images using a CNN trained on ImageNet.
Based on the paper: [Colorful Image Colorization](http://richzhang.github.io/colorization/)
by Richard Zhang, Phillip Isola, Alexei A. Efros (ECCV 2016).

The network takes the L channel of a LAB image as input and predicts the
ab channels, which are then merged back with L to produce a full-color output.

## Model Details
- **Architecture**: Custom CNN (VGG-style encoder + dilated convolutions)
- **Input**: Grayscale image (L channel of LAB), 224×224
- **Output**: ab channels, upsampled to original size
- **Framework**: ONNX (converted from original Caffe model)
- **Original weights**: http://eecs.berkeley.edu/~rich.zhang/projects/2016_colorization/

## Usage

### Python
```bash
python demo.py --model colorization_deploy_v2_2026april.onnx --image example_outputs/input_image.jpg --output example_outputs/output_image.png
```

Or import directly:
```python
import cv2

net = cv2.dnn.readNet("colorization_deploy_v2_2026apr.onnx")
# see demo.py for full inference pipeline
```

## License
See [LICENSE](./LICENSE) — original model is released under BSD license by Richard Zhang.

## References
- Paper: https://arxiv.org/abs/1603.08511
- Original repo: https://github.com/richzhang/colorization