Semantic and Geometric Unfolding of StyleGAN Latent Space

TL;DR

This paper introduces a novel method using normalizing flows to learn a proxy latent space for StyleGAN, addressing geometric and disentanglement limitations to improve face image editing.

Contribution

It proposes a new approach to enhance StyleGAN's latent space by learning a proxy space with normalizing flows, improving image editing capabilities.

Findings

Better alignment of latent space with perceptual distances

Improved disentanglement of facial attributes

Enhanced face image editing performance

Abstract

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.