Semantic and Geometric Unfolding of StyleGAN Latent Space

07/09/2021
by   Mustafa Shukor, et al.
33

Generative adversarial networks (GANs) have proven to be surprisingly efficient for image editing by inverting and manipulating the latent code corresponding to a natural image. This property emerges from the disentangled nature of the latent space. In this paper, we identify two geometric limitations of such latent space: (a) euclidean distances differ from image perceptual distance, and (b) disentanglement is not optimal and facial attribute separation using linear model is a limiting hypothesis. We thus propose a new method to learn a proxy latent representation using normalizing flows to remedy these limitations, and show that this leads to a more efficient space for face image editing.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset