GAN Prior Embedded Network for Blind Face Restoration in the Wild

CVPR 2021  ยท  Tao Yang, Peiran Ren, Xuansong Xie, Lei Zhang ยท

Blind face restoration (BFR) from severely degraded face images in the wild is a very challenging problem. Due to the high illness of the problem and the complex unknown degradation, directly training a deep neural network (DNN) usually cannot lead to acceptable results. Existing generative adversarial network (GAN) based methods can produce better results but tend to generate over-smoothed restorations. In this work, we propose a new method by first learning a GAN for high-quality face image generation and embedding it into a U-shaped DNN as a prior decoder, then fine-tuning the GAN prior embedded DNN with a set of synthesized low-quality face images. The GAN blocks are designed to ensure that the latent code and noise input to the GAN can be respectively generated from the deep and shallow features of the DNN, controlling the global face structure, local face details and background of the reconstructed image. The proposed GAN prior embedded network (GPEN) is easy-to-implement, and it can generate visually photo-realistic results. Our experiments demonstrated that the proposed GPEN achieves significantly superior results to state-of-the-art BFR methods both quantitatively and qualitatively, especially for the restoration of severely degraded face images in the wild. The source code and models can be found at https://github.com/yangxy/GPEN.

PDF Abstract CVPR 2021 PDF CVPR 2021 Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Blind Face Restoration CelebA-HQ GPEN PSNR 20.80 # 4
FID 31.72 # 1
LPIPS 0.346 # 1
Blind Face Restoration CelebA-HQ GWAInet PSNR 19.84 # 6
FID 135.84 # 5
LPIPS 0.569 # 4
Blind Face Restoration CelebA-HQ GFRNet PSNR 21.70 # 1
FID 134.92 # 4
LPIPS 0.597 # 5
Blind Face Restoration CelebA-HQ HiFaceGAN PSNR 21.33 # 3
FID 56.67 # 2
LPIPS 0.392 # 2
Blind Face Restoration CelebA-HQ Super-FAN PSNR 21.56 # 2
FID 136.83 # 6
LPIPS 0.616 # 6
Blind Face Restoration CelebA-HQ Pix2PixHD PSNR 20.45 # 5
FID 76.89 # 3
LPIPS 0.494 # 3

Methods


No methods listed for this paper. Add relevant methods here