User-Controllable Latent Transformer for StyleGAN Image Layout Editing
Loading...
Date
2022
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association and John Wiley & Sons Ltd.
Abstract
Latent space exploration is a technique that discovers interpretable latent directions and manipulates latent codes to edit various attributes in images generated by generative adversarial networks (GANs). However, in previous work, spatial control is limited to simple transformations (e.g., translation and rotation), and it is laborious to identify appropriate latent directions and adjust their parameters. In this paper, we tackle the problem of editing the StyleGAN image layout by annotating the image directly. To do so, we propose an interactive framework for manipulating latent codes in accordance with the user inputs. In our framework, the user annotates a StyleGAN image with locations they want to move or not and specifies a movement direction by mouse dragging. From these user inputs and initial latent codes, our latent transformer based on a transformer encoderdecoder architecture estimates the output latent codes, which are fed to the StyleGAN generator to obtain a result image. To train our latent transformer, we utilize synthetic data and pseudo-user inputs generated by off-the-shelf StyleGAN and optical flow models, without manual supervision. Quantitative and qualitative evaluations demonstrate the effectiveness of our method over existing methods.
Description
CCS Concepts: Computing methodologies --> Artificial intelligence; Image manipulation
@article{10.1111:cgf.14686,
journal = {Computer Graphics Forum},
title = {{User-Controllable Latent Transformer for StyleGAN Image Layout Editing}},
author = {Endo, Yuki},
year = {2022},
publisher = {The Eurographics Association and John Wiley & Sons Ltd.},
ISSN = {1467-8659},
DOI = {10.1111/cgf.14686}
}