Attribute-conditioned Layout GAN for Automatic Graphic Design

TL;DR

This paper presents Attribute-conditioned Layout GAN, a novel method for automatic graphic layout generation that incorporates element attributes and adapts to size changes, validated through user studies.

Contribution

It introduces an attribute-conditioned GAN framework with element dropout and new loss functions for improved graphic layout synthesis.

Findings

Successfully generates layouts conditioned on element attributes.

Adjusts layouts to new sizes while maintaining reading order.

Validated effectiveness through user study.

Abstract

Modeling layout is an important first step for graphic design. Recently, methods for generating graphic layouts have progressed, particularly with Generative Adversarial Networks (GANs). However, the problem of specifying the locations and sizes of design elements usually involves constraints with respect to element attributes, such as area, aspect ratio and reading-order. Automating attribute conditional graphic layouts remains a complex and unsolved problem. In this paper, we introduce Attribute-conditioned Layout GAN to incorporate the attributes of design elements for graphic layout generation by forcing both the generator and the discriminator to meet attribute conditions. Due to the complexity of graphic designs, we further propose an element dropout method to make the discriminator look at partial lists of elements and learn their local patterns. In addition, we introduce various loss designs following different design principles for layout optimization. We demonstrate that the proposed method can synthesize graphic layouts conditioned on different element attributes. It can also adjust well-designed layouts to new sizes while retaining elements' original reading-orders. The effectiveness of our method is validated through a user study.