Automatic Text Box Placement for Supporting Typographic Design
Preprint
Abstract
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.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- Retrieval-Augmented Layout Transformer for Content-Aware Layout Generation2024
- Relation-Aware Diffusion Model for Controllable Poster Layout Generation2023
- Towards Flexible Multi-modal Document Models2023
- LayoutDM: Discrete Diffusion Model for Controllable Layout Generation2023
- LayoutPrompter: Awaken the Design Ability of Large Language Models2023
- LayoutGPT: Compositional Visual Planning and Generation with Large Language Models2023
- CanvasVAE: Learning to Generate Vector Graphic Documents2021
- Harmonious Textual Layout Generation Over Natural Images via Deep Aesthetics LearningIEEE Transactions on Multimedia, 2021
- Distance-IoU Loss: Faster and Better Learning for Bounding Box RegressionProceedings of the AAAI Conference on Artificial Intelligence, 2020
- LayoutVAE: Stochastic Scene Layout Generation From a Label Set2019