loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Syuusuke Ishihata ; Ryohei Orihara ; Yuichi Sei ; Yasuyuki Tahara and Akihiko Ohsuga

Affiliation: The University of Electro-Communications, Tokyo, Japan

Keyword(s): StyleGAN, GAN Inversion, Image Editing.

Abstract: Recently, research has been conducted on applying StyleGAN to image editing tasks. Although the technique can be applied to editing background images, because they are more diverse than foreground images such as face images, specifying an object in background images to be edited is difficult. For example, because natural language instructions can be ambiguous, edited images become undesirable for the user. It is challenging to resolve style and content dependencies in image editing. In our study, we propose an editing method that adapts Style Transformer, the latest GAN inversion encoder approach, to HyperStyle by introducing semantic segmentation to maintain the reconstruction quality and separate the style and the content of the background image. The content is edited while keeping the original style by manipulating the coarse part of latent variables and the residual parameters obtained by HyperStyle, and the style is edited without changing the content by manipulating the medium and fine part of latent vectors as in the conventional StyleGAN. As a result, the qualitative evaluation confirms that our model enabled the editing of image content and style separately, and the quantitative evaluation validates that the reconstruction quality is comparable to the conventional method. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.15.239.145

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Ishihata, S.; Orihara, R.; Sei, Y.; Tahara, Y. and Ohsuga, A. (2023). Background Image Editing with HyperStyle and Semantic Segmentation. In Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART; ISBN 978-989-758-623-1; ISSN 2184-433X, SciTePress, pages 293-300. DOI: 10.5220/0011661500003393

@conference{icaart23,
author={Syuusuke Ishihata. and Ryohei Orihara. and Yuichi Sei. and Yasuyuki Tahara. and Akihiko Ohsuga.},
title={Background Image Editing with HyperStyle and Semantic Segmentation},
booktitle={Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART},
year={2023},
pages={293-300},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011661500003393},
isbn={978-989-758-623-1},
issn={2184-433X},
}

TY - CONF

JO - Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART
TI - Background Image Editing with HyperStyle and Semantic Segmentation
SN - 978-989-758-623-1
IS - 2184-433X
AU - Ishihata, S.
AU - Orihara, R.
AU - Sei, Y.
AU - Tahara, Y.
AU - Ohsuga, A.
PY - 2023
SP - 293
EP - 300
DO - 10.5220/0011661500003393
PB - SciTePress