GFP-GAN
GFPGAN aims at developing a Practical Algorithm for Real-world Face Restoration. It leverages rich and diverse priors encapsulated in a pretrained face GAN (e.g., StyleGAN2) for blind face restoration.
Description
I am sharing a colab notebook which I had used to experiment and see the results of GFP-GAN from https://github.com/TencentARC/GFPGAN using my childhood images.
My Results
Input:
Output:
Citation
@InProceedings{wang2021gfpgan, author = {Xintao Wang and Yu Li and Honglun Zhang and Ying Shan}, title = {Towards Real-World Blind Face Restoration with Generative Facial Prior}, booktitle={The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2021} }
License
Please follow the licensing available at https://github.com/TencentARC/GFPGAN