通过消融实验发现，分镜布局是定义漫画风格的核心视觉特征。
How Panel Layouts Define Manga: Insights from Visual Ablation Experiments
- 用分镜框信息训练模型预测漫画标题，量化分析布局作用
- 在104部作品、12种类型中，布局特征可准确区分不同漫画
- 适合对漫画视觉语言、创作规律感兴趣的读者
如今，漫画已在全球范围内广受欢迎。然而，漫画中的角色、文字与分镜布局等元素如何体现作品的独特性，甚至定义一部作品，仍是未被深入探索的领域。本文旨在通过定量与定性方法分析漫画的视觉特征，重点关注分镜布局。研究以漫画对页图像为输入，训练深度学习模型预测漫画标题，并通过分类准确率进行量化分析。具体地，通过限制输入仅保留分镜框信息，开展消融实验以研究分镜布局特征。基于Manga109数据集中的104部作品、12个类型及10,122张对页图像，结合Grad-CAM进行定性分析，结果表明：漫画的独特性强烈体现在其分镜布局中。
原文摘要 · Abstract (English)
Today, manga has gained worldwide popularity. However, the question of how various elements of manga, such as characters, text, and panel layouts, reflect the uniqueness of a particular work, or even define it, remains an unexplored area. In this paper, we aim to quantitatively and qualitatively analyze the visual characteristics of manga works, with a particular focus on panel layout features. As a research method, we used facing page images of manga as input to train a deep learning model for predicting manga titles, examining classification accuracy to quantitatively analyze these features. Specifically, we conducted ablation studies by limiting page image information to panel frames to analyze the characteristics of panel layouts. Through a series of quantitative experiments using all 104 works, 12 genres, and 10,122 facing page images from the Manga109 dataset, as well as qualitative analysis using Grad-CAM, our study demonstrates that the uniqueness of manga works is strongly reflected in their panel layouts.
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。