StyleHumanCLIP: Text-Guided Garment Manipulation for StyleGAN-Human

Takato Yoshikawa, Yuki Endo, Yoshihiro Kanamori

2024

Abstract

This paper tackles text-guided control of StyleGAN for editing garments in full-body human images. Existing StyleGAN-based methods suffer from handling the rich diversity of garments and body shapes and poses. We propose a framework for text-guided full-body human image synthesis via an attention-based latent code mapper, which enables more disentangled control of StyleGAN than existing mappers. Our latent code mapper adopts an attention mechanism that adaptively manipulates individual latent codes on different StyleGAN layers under text guidance. In addition, we introduce feature-space masking at inference time to avoid unwanted changes caused by text inputs. Our quantitative and qualitative evaluations reveal that our method can control generated images more faithfully to given texts than existing methods.

Paper Citation

in Harvard Style

Yoshikawa T., Endo Y. and Kanamori Y. (2024). StyleHumanCLIP: Text-Guided Garment Manipulation for StyleGAN-Human. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP; ISBN 978-989-758-679-8, SciTePress, pages 59-70. DOI: 10.5220/0012304600003660

in Bibtex Style

@conference{visapp24,
author={Takato Yoshikawa and Yuki Endo and Yoshihiro Kanamori},
title={StyleHumanCLIP: Text-Guided Garment Manipulation for StyleGAN-Human},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP},
year={2024},
pages={59-70},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012304600003660},
isbn={978-989-758-679-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP
TI - StyleHumanCLIP: Text-Guided Garment Manipulation for StyleGAN-Human
SN - 978-989-758-679-8
AU - Yoshikawa T.
AU - Endo Y.
AU - Kanamori Y.
PY - 2024
SP - 59
EP - 70
DO - 10.5220/0012304600003660
PB - SciTePress