Semantic and Geometric Unfolding of StyleGAN Latent Space
This work addresses inefficiencies in face image editing for users of GAN-based tools, though it is incremental as it builds on existing StyleGAN frameworks.
The paper tackled the geometric limitations of StyleGAN's latent space, such as mismatched Euclidean and perceptual distances and suboptimal disentanglement, by proposing a method using normalizing flows to learn a proxy representation, resulting in a more efficient space for face image editing.
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.