Arxiv Preprint | Supplementary Video
WebCam Video Demo [Offline][Colab] | Custom Video Demo [Offline] | Image Demo [WebGUI][Colab]
### Image Matting
We provide an [online Colab demo](https://colab.research.google.com/drive/1GANpbKT06aEFiW-Ssx0DQnnEADcXwQG6?usp=sharing) for portrait image matting.
It allows you to upload portrait images and predict/visualize/download the alpha mattes.
### Community
Here we share some cool applications/extentions of MODNet built by the community.
- **WebGUI for Image Matting**
You can try [this WebGUI](https://www.gradio.app/hub/aliabd/modnet) (hosted on [Gradio](https://www.gradio.app/)) for portrait matting from your browser without code!
- **Colab Demo of Bokeh (Blur Background)**
You can try [this Colab demo](https://colab.research.google.com/github/eyaler/avatars4all/blob/master/yarok.ipynb) (built by [@eyaler](https://github.com/eyaler)) to blur the backgroud based on MODNet!
- **ONNX Version of MODNet**
You can convert the pre-trained MODNet to an ONNX model by using [this code](onnx) (provided by [@manthan3C273](https://github.com/manthan3C273)). You can also try [this Colab demo](https://colab.research.google.com/drive/1P3cWtg8fnmu9karZHYDAtmm1vj1rgA-f?usp=sharing) for MODNet image matting (ONNX version).
- **TorchScript Version of MODNet**
You can convert the pre-trained MODNet to an TorchScript model by using [this code](torchscript) (provided by [@yarkable](https://github.com/yarkable)).
## Code
We provide the [code](src/trainer.py) of MODNet training iteration, including:
- **Supervised Training**: Train MODNet on a labeled matting dataset
- **SOC Adaptation**: Adapt a trained MODNet to an unlabeled dataset
In the function comments, we provide examples of how to call the function.
## TODO
- Release the code of One-Frame Delay
- Release PPM-100 validation benchmark (**Delayed, But On The Way...**)
**NOTE**: PPM-100 is a **validation set**. Our training set will not be published.
## License
This project (**code, pre-trained models, demos, *etc.***) is released under the [Creative Commons Attribution NonCommercial ShareAlike 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode) license.
**NOTE**: The license will be changed to allow commercial use after this work is accepted by a conference or a journal.
## Acknowledgement
- We thank [City University of Hong Kong](https://www.cityu.edu.hk/) and [SenseTime](https://www.sensetime.com/) for their support to this project.
- We thank
[the Gradio team](https://github.com/gradio-app/gradio), [@eyaler](https://github.com/eyaler), [@manthan3C273](https://github.com/manthan3C273), [@yarkable](https://github.com/yarkable),
for their contributions to this repository or their cool applications based on MODNet.
## Citation
If this work helps your research, please consider to cite:
```bibtex
@article{MODNet,
author = {Zhanghan Ke and Kaican Li and Yurou Zhou and Qiuhua Wu and Xiangyu Mao and Qiong Yan and Rynson W.H. Lau},
title = {Is a Green Screen Really Necessary for Real-Time Portrait Matting?},
journal={ArXiv},
volume={abs/2011.11961},
year = {2020},
}
```
## Contact
This project is currently maintained by Zhanghan Ke ([@ZHKKKe](https://github.com/ZHKKKe)).
If you have any questions, please feel free to contact `kezhanghan@outlook.com`.