Editing existing images requires embedding a given image into the latent space of StyleGAN2.
Correspondence between images is a fundamental problem in computer vision, with a variety of graphics applications.
Learning a good image prior is a long-term goal for image restoration and manipulation.
We propose an efficient algorithm to embed a given image into the latent space of StyleGAN.
Image interpolation, or image morphing, refers to a visual transition between two (or more) input images.