yangxy / gpen

Blind Face Restoration in the Wild

  • Public
  • 163.1K runs
  • T4
  • GitHub
  • Paper

Input

image
*file

Input image

string

Choose a task.

Default: "Face Restoration"

boolean

whether outputs individual enhanced faces.

Default: false

boolean

whether the input image is broken, valid for Face Inpainting. When set to True, the output will be the 'fixed' image. When set to False, the image will randomly add brush strokes to simulate a broken image and the output will be broken + fixed image

Default: true

Output

file

This example was created by a different version, yangxy/gpen:2210792a.

Run time and cost

This model costs approximately $0.026 to run on Replicate, or 38 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia T4 GPU hardware. Predictions typically complete within 116 seconds. The predict time for this model varies significantly based on the inputs.

Readme

GAN Prior Embedded Network for Blind Face Restoration in the Wild

Paper | Supplementary | Demo

Tao Yang, Peiran Ren, Xuansong Xie, Lei Zhang DAMO Academy, Alibaba Group, Hangzhou, China Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China

Main idea

Citation

If our work is useful for your research, please consider citing:

@inproceedings{Yang2021GPEN,
    title={GAN Prior Embedded Network for Blind Face Restoration in the Wild},
    author={Tao Yang, Peiran Ren, Xuansong Xie, and Lei Zhang},
    booktitle={IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
    year={2021}
}

License

© Alibaba, 2021. For academic and non-commercial use only.

Acknowledgments

We borrow some codes from Pytorch_Retinaface and stylegan2-pytorch.

Contact

If you have any questions or suggestions about this paper, feel free to reach me at yangtao9009@gmail.com.