Can GPTs Evaluate Graphic Design Based on Design Principles?

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Haraguchi, Daichi, Inoue, Naoto, Shimoda, Wataru, Mitani, Hayato, Uchida, Seiichi, Yamaguchi, Kota
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917800804614144
author Haraguchi, Daichi
Inoue, Naoto
Shimoda, Wataru
Mitani, Hayato
Uchida, Seiichi
Yamaguchi, Kota
author_facet Haraguchi, Daichi
Inoue, Naoto
Shimoda, Wataru
Mitani, Hayato
Uchida, Seiichi
Yamaguchi, Kota
contents Recent advancements in foundation models show promising capability in graphic design generation. Several studies have started employing Large Multimodal Models (LMMs) to evaluate graphic designs, assuming that LMMs can properly assess their quality, but it is unclear if the evaluation is reliable. One way to evaluate the quality of graphic design is to assess whether the design adheres to fundamental graphic design principles, which are the designer's common practice. In this paper, we compare the behavior of GPT-based evaluation and heuristic evaluation based on design principles using human annotations collected from 60 subjects. Our experiments reveal that, while GPTs cannot distinguish small details, they have a reasonably good correlation with human annotation and exhibit a similar tendency to heuristic metrics based on design principles, suggesting that they are indeed capable of assessing the quality of graphic design. Our dataset is available at https://cyberagentailab.github.io/Graphic-design-evaluation .
format Preprint
id arxiv_https___arxiv_org_abs_2410_08885
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Can GPTs Evaluate Graphic Design Based on Design Principles?
Haraguchi, Daichi
Inoue, Naoto
Shimoda, Wataru
Mitani, Hayato
Uchida, Seiichi
Yamaguchi, Kota
Computer Vision and Pattern Recognition
Graphics
Recent advancements in foundation models show promising capability in graphic design generation. Several studies have started employing Large Multimodal Models (LMMs) to evaluate graphic designs, assuming that LMMs can properly assess their quality, but it is unclear if the evaluation is reliable. One way to evaluate the quality of graphic design is to assess whether the design adheres to fundamental graphic design principles, which are the designer's common practice. In this paper, we compare the behavior of GPT-based evaluation and heuristic evaluation based on design principles using human annotations collected from 60 subjects. Our experiments reveal that, while GPTs cannot distinguish small details, they have a reasonably good correlation with human annotation and exhibit a similar tendency to heuristic metrics based on design principles, suggesting that they are indeed capable of assessing the quality of graphic design. Our dataset is available at https://cyberagentailab.github.io/Graphic-design-evaluation .
title Can GPTs Evaluate Graphic Design Based on Design Principles?
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2410.08885