Attribute-Conditioned Layout GAN for Automatic Graphic Design

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.

Deep Learning for Document Layout Generation: A First Reproducible Quantitative Evaluation and a Baseline Model

“…In [7], absolute alignment and overlap scores are provided for generated document layouts but the dataset on which these scores have been obtained, referred only as "the document layout dataset", has not been made available. The exact same problem is found in [8] where alignment and overlap scores are given for a private advertising layout dataset, not available to the scientific community.…”

“…It can generate layouts of documents, layouts of pixels subset (extracted from MNIST handwritten digits images), clipart scenes and geometric tangrams. In [8], authors extend [7] previous work to propose two main applications : layout generation and layout adjustment. Layout generation is split into three sub-applications.…”

GUIGAN: Learning to Generate GUI Designs Using Generative Adversarial Networks

“…There are no existing evaluation metrics for mobile GUI design in the literature. But inspired by the web GUI evaluation [37]- [39] and image evaluation [40], [41], we propose three novel metrics for participants to rate the quality of the GUI design from three aspects by considering the characteristics of the mobile GUIs. First, design aesthetics is to evaluate the overall design's pleasing qualities.…”

Big Data driven Product Design: A Survey

“…For example, clothing design, which needs to show the effect of try-on. In addition to generating product images, GAN and its extended models can also apply to layout generation, such as indoors [205,206] and web pages [207].…”