自动排版中，模型如何智能放置文字框更美观高效？
Automatic Text Box Placement for Supporting Typographic Design
- 用Transformer处理多图信息，提升布局理解能力
- 标准Transformer在Crello数据集上表现优于大视觉语言模型
- 小文字和密集布局仍是挑战，适合设计自动化研究者
在广告和网页布局设计中，视觉吸引力与传播效率的平衡至关重要。本研究探讨不完整布局下的自动文本框放置，对比了标准Transformer模型、小型视觉语言模型Phi3.5-vision、大型预训练视觉语言模型Gemini以及扩展的多图像处理Transformer。在Crello数据集上的评估显示，标准Transformer模型总体优于基于VLM的方法，尤其在引入更丰富的外观信息时表现更佳。然而，所有方法在处理极小文字或高密度布局时仍面临困难。研究结果凸显任务专用架构的优势，并为自动化布局设计的进一步优化提供了方向。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。