In layout design for advertisements and web pages, balancing visual appeal and communication efficiency is crucial. This study examines automated text box placement in incomplete layouts, comparing a standard Transformer-based method, a small Vision and Language Model (Phi3.5-vision), a large pretrained VLM (Gemini), and an extended Transformer that processes multiple images. Evaluations on the Crello dataset show the standard Transformer-based models generally outperform VLM-based approaches, particularly when incorporating richer appearance information. However, all methods face challenges with very small text or densely populated layouts. These findings highlight the benefits of task-specific architectures and suggest avenues for further improvement in automated layout design.
Cite
@article{arxiv.2510.07665,
title = {Automatic Text Box Placement for Supporting Typographic Design},
author = {Jun Muraoka and Daichi Haraguchi and Naoto Inoue and Wataru Shimoda and Kota Yamaguchi and Seiichi Uchida},
journal= {arXiv preprint arXiv:2510.07665},
year = {2025}
}