Element-Conditioned Gan for Graphic Layout Generation

24 Pages Posted: 29 Nov 2023

See all articles by Yunzhan Zhou

Yunzhan Zhou

Durham University

Qianzhi Jing

Zhejiang University

Zhaoxing Li

University of Southampton

Lei Shi

Newcastle University; Durham University

Liuqing Chen

Zhejiang University

Lingyun Sun

Zhejiang University

Abstract

Layout guides the position and scale of design elements for desirable aesthetics and effective demonstration. Recently, Generative Adversarial Networks (GANs) have proved their capability in generating effective layouts. However, current GANs ignore the situation where the amounts and types of the input design elements are given and determined. In this paper, we propose EcGAN, an element-conditioned GAN for graphic layout generation conditioned on specified design elements (design elements’ amount and types). We represent each element by a bounding box and propose three components: element mask, element condition loss and two-step discriminators, to solve the bounding box modelling problem for element-conditioned layout generation. Experiments reveal that EcGAN outperforms existing methods quantitatively and qualitatively. We also perform detailed ablation studies to highlight the effect of each component and a user study to further validate our model. Finally, we demonstrate two of EcGAN’s applications for practical design scenarios.

Keywords: generative adversarial networks, graphic design, layout

Suggested Citation

Zhou, Yunzhan and Jing, Qianzhi and Li, Zhaoxing and Shi, Lei and Chen, Liuqing and Sun, Lingyun, Element-Conditioned Gan for Graphic Layout Generation. Available at SSRN: https://ssrn.com/abstract=4648075 or http://dx.doi.org/10.2139/ssrn.4648075

Yunzhan Zhou (Contact Author)

Durham University ( email )

Old Elvet
Mill Hill Lane
Durham, DH1 3HP
United Kingdom

Qianzhi Jing

Zhejiang University ( email )

38 Zheda Road
Hangzhou, 310058
China

Zhaoxing Li

University of Southampton ( email )

Southampton Business School
Southampton
United Kingdom

Lei Shi

Newcastle University ( email )

Durham University ( email )

Durham, DH1 3LE
Great Britain

Liuqing Chen

Zhejiang University ( email )

38 Zheda Road
Hangzhou, 310058
China

Lingyun Sun

Zhejiang University ( email )

38 Zheda Road
Hangzhou, 310058
China

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
35
Abstract Views
114
PlumX Metrics