StyleGAN is now capable of achieving excellent results, especially high-quality face synthesis. Recently, some studies have tried to invert real face images into style latent space via StyleGAN. However, morphing real faces via latent representation is still in its infancy. Training costs are high and/or require huge samples with labels. By adding regularization to style optimization, we propose a novel method to morph real faces based on StyleGAN. To do the supervised task, we label latent vectors via synthesized faces and release the label set; then we utilise logistic regression to fast discover interpretable directions in latent space. Appropriate regularization helps us to optimize both latent vectors (faces and directions). Moreover, we use learned directions under different layer representations to handle real face morphing. Compared to the existing methods, our method faster yields a larger diverse and realistic output. Code and cases are available at \url{https://github.com/disanda/RFM}.

Finely tuned deep generative adversarial networks (GANs) can generate high-quality (HQ) images. However, the discriminator in GAN is only able to distinguish true or fake images. Moreover, numerous synthesized images from GANs are imperfect, and we can not reconstruct those images via GANs. In this paper, we revisit pre-trained GANs and offer a self-supervised method to quickly transform GAN’s discriminators into encoders. We reuse parameters of the GAN’s discriminator and replace its output layer, so that it can be transformed into an encoder and output reformed latent vectors. The transformation makes the pre-trained GAN a symmetrical architecture and allows for better performance. Based on the method, GANs can be made to reconstruct synthesized images via encoders. Compared to synthesized images, these reconstructions can maintain or even attain higher quality.