Paper ID: 2206.14892 • Published Jun 29, 2022

Semantic Unfolding of StyleGAN Latent Space

Mustafa Shukor, Xu Yao, Bharath Bushan Damodaran, Pierre Hellier
TL;DR
Get AI-generated summaries with premium
Get AI-generated summaries with premium
Generative adversarial networks (GANs) have proven to be surprisingly efficient for image editing by inverting and manipulating the latent code corresponding to an input real image. This editing property emerges from the disentangled nature of the latent space. In this paper, we identify that the facial attribute disentanglement is not optimal, thus facial editing relying on linear attribute separation is flawed. We thus propose to improve semantic disentanglement with supervision. Our method consists in learning a proxy latent representation using normalizing flows, and we show that this leads to a more efficient space for face image editing.