Multi-level Latent Space Structuring for Generative Control

Truncation is widely used in generative models for improving the quality of the generated samples, at the expense of reducing their diversity. We propose to leverage the StyleGAN generative architecture to devise a new truncation technique, based on a decomposition of the latent space into clusters,...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2022-02
Main Authors: Katzir, Oren, Perepelook, Vicky, Lischinski, Dani, Cohen-Or, Daniel
Format: Article
Language:English
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Truncation is widely used in generative models for improving the quality of the generated samples, at the expense of reducing their diversity. We propose to leverage the StyleGAN generative architecture to devise a new truncation technique, based on a decomposition of the latent space into clusters, enabling customized truncation to be performed at multiple semantic levels. We do so by learning to re-generate W-space, the extended intermediate latent space of StyleGAN, using a learnable mixture of Gaussians, while simultaneously training a classifier to identify, for each latent vector, the cluster that it belongs to. The resulting truncation scheme is more faithful to the original untruncated samples and allows a better trade-off between quality and diversity. We compare our method to other truncation approaches for StyleGAN, both qualitatively and quantitatively.
ISSN:2331-8422