Semantic and Geometric Unfolding of StyleGAN Latent Space

Autor:	Shukor, Mustafa, Yao, Xu, Damodaran, Bharath Bhushan, Hellier, Pierre
Rok vydání:	2021
Předmět:	Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	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. Comment: 16 pages
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2107.04481 Zobrazit plný text záznamu View this record from Arxiv