Automatic Text Box Placement for Supporting Typographic Design
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916997959254016 |
|---|---|
| author | Muraoka, Jun Haraguchi, Daichi Inoue, Naoto Shimoda, Wataru Yamaguchi, Kota Uchida, Seiichi |
| author_facet | Muraoka, Jun Haraguchi, Daichi Inoue, Naoto Shimoda, Wataru Yamaguchi, Kota Uchida, Seiichi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_07665 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Automatic Text Box Placement for Supporting Typographic Design Muraoka, Jun Haraguchi, Daichi Inoue, Naoto Shimoda, Wataru Yamaguchi, Kota Uchida, Seiichi Computer Vision and Pattern Recognition 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. |
| title | Automatic Text Box Placement for Supporting Typographic Design |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.07665 |