The Layout Generation Algorithm of Graphic Design Based on Transformer-CVAE

TL;DR

This paper introduces LayoutT-CVAE, an innovative Transformer-CVAE model for automatic graphic design layout generation, improving efficiency, controllability, and creativity in interface design tasks.

Contribution

It presents a novel end-to-end layout generation model with element and feature disentanglement strategies, incorporating new principles and metrics for enhanced control and interpretability.

Findings

Outperforms existing models on multiple metrics

Enhances controllability and interpretability of layout generation

Significantly improves efficiency in graphic design tasks

Abstract

Graphic design is ubiquitous in people's daily lives. For graphic design, the most time-consuming task is laying out various components in the interface. Repetitive manual layout design will waste a lot of time for professional graphic designers. Existing templates are usually rudimentary and not suitable for most designs, reducing efficiency and limiting creativity. This paper implemented the Transformer model and conditional variational autoencoder (CVAE) to the graphic design layout generation task. It proposed an end-to-end graphic design layout generation model named LayoutT-CVAE. We also proposed element disentanglement and feature-based disentanglement strategies and introduce new graphic design principles and similarity metrics into the model, which significantly increased the controllability and interpretability of the deep model. Compared with the existing state-of-art models, the layout generated by ours performs better on many metrics.