Automatic Layout Planning for Visually-Rich Documents with Instruction-Following Models

TL;DR

This paper presents a multimodal instruction-following framework that enables non-professional users to create visually appealing layouts for rich documents by specifying design parameters, outperforming GPT-4V in layout accuracy.

Contribution

The work introduces a novel multimodal model for layout planning that understands and executes user instructions, advancing automation in graphic design for non-experts.

Findings

Outperforms GPT-4V with 12% higher mIoU on Crello benchmark.

Develops three layout reasoning tasks for training the model.

Simplifies the design process for non-professional users.

Abstract

Recent advancements in instruction-following models have made user interactions with models more user-friendly and efficient, broadening their applicability. In graphic design, non-professional users often struggle to create visually appealing layouts due to limited skills and resources. In this work, we introduce a novel multimodal instruction-following framework for layout planning, allowing users to easily arrange visual elements into tailored layouts by specifying canvas size and design purpose, such as for book covers, posters, brochures, or menus. We developed three layout reasoning tasks to train the model in understanding and executing layout instructions. Experiments on two benchmarks show that our method not only simplifies the design process for non-professionals but also surpasses the performance of few-shot GPT-4V models, with mIoU higher by 12% on Crello. This progress highlights the potential of multimodal instruction-following models to automate and simplify the design process, providing an approachable solution for a wide range of design tasks on visually-rich documents.