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

page 2

page 6

page 7

page 8

page 13

page 14

page 15

page 16

research
06/29/2022

Semantic Unfolding of StyleGAN Latent Space

Generative adversarial networks (GANs) have proven to be surprisingly ef...
research
11/05/2020

Transforming Facial Weight of Real Images by Editing Latent Space of StyleGAN

We present an invert-and-edit framework to automatically transform facia...
research
04/12/2023

VidStyleODE: Disentangled Video Editing via StyleGAN and NeuralODEs

We propose VidStyleODE, a spatiotemporally continuous disentangled Video...
research
05/12/2022

Tensor-based Emotion Editing in the StyleGAN Latent Space

In this paper, we use a tensor model based on the Higher-Order Singular ...
research
11/26/2022

Deep Curvilinear Editing: Commutative and Nonlinear Image Manipulation for Pretrained Deep Generative Model

Semantic editing of images is the fundamental goal of computer vision. A...
research
03/18/2021

Using latent space regression to analyze and leverage compositionality in GANs

In recent years, Generative Adversarial Networks have become ubiquitous ...
research
12/02/2022

LatentSwap3D: Semantic Edits on 3D Image GANs

Recent 3D-aware GANs rely on volumetric rendering techniques to disentan...

Please sign up or login with your details

Forgot password? Click here to reset