GAN Inversion: A Survey
It addresses the need for bridging real and fake image domains to enhance image editing capabilities, but it is incremental as it surveys existing techniques rather than introducing new methods.
This survey paper tackles the problem of inverting real images into the latent space of pretrained GAN models like StyleGAN and BigGAN to enable faithful reconstruction and editing, providing an overview of recent algorithms and applications in image restoration and manipulation.
GAN inversion aims to invert a given image back into the latent space of a pretrained GAN model, for the image to be faithfully reconstructed from the inverted code by the generator. As an emerging technique to bridge the real and fake image domains, GAN inversion plays an essential role in enabling the pretrained GAN models such as StyleGAN and BigGAN to be used for real image editing applications. Meanwhile, GAN inversion also provides insights on the interpretation of GAN's latent space and how the realistic images can be generated. In this paper, we provide an overview of GAN inversion with a focus on its recent algorithms and applications. We cover important techniques of GAN inversion and their applications to image restoration and image manipulation. We further elaborate on some trends and challenges for future directions.