English

PCA-SRGAN: Incremental Orthogonal Projection Discrimination for Face Super-resolution

Computer Vision and Pattern Recognition 2020-08-31 v2

Abstract

Generative Adversarial Networks (GAN) have been employed for face super resolution but they bring distorted facial details easily and still have weakness on recovering realistic texture. To further improve the performance of GAN based models on super-resolving face images, we propose PCA-SRGAN which pays attention to the cumulative discrimination in the orthogonal projection space spanned by PCA projection matrix of face data. By feeding the principal component projections ranging from structure to details into the discriminator, the discrimination difficulty will be greatly alleviated and the generator can be enhanced to reconstruct clearer contour and finer texture, helpful to achieve the high perception and low distortion eventually. This incremental orthogonal projection discrimination has ensured a precise optimization procedure from coarse to fine and avoids the dependence on the perceptual regularization. We conduct experiments on CelebA and FFHQ face datasets. The qualitative visual effect and quantitative evaluation have demonstrated the overwhelming performance of our model over related works.

Keywords

Cite

@article{arxiv.2005.00306,
  title  = {PCA-SRGAN: Incremental Orthogonal Projection Discrimination for Face Super-resolution},
  author = {Hao Dou and Chen Chen and Xiyuan Hu and Zuxing Xuan and Zhisen Hu and Silong Peng},
  journal= {arXiv preprint arXiv:2005.00306},
  year   = {2020}
}
R2 v1 2026-06-23T15:14:14.717Z