PCA-SRGAN: Incremental Orthogonal Projection Discrimination for Face Super-resolution
This work addresses face super-resolution for applications like image enhancement, but it appears incremental as it builds on existing GAN methods with a novel discrimination technique.
The paper tackled the problem of distorted facial details and unrealistic texture in GAN-based face super-resolution by proposing PCA-SRGAN, which uses incremental orthogonal projection discrimination to enhance the generator, resulting in improved visual effects and quantitative performance on CelebA and FFHQ datasets.
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.