[论文] Manga2Animate: An Agentic Framework for Faithful Manga Animation with ...

论文概要

研究领域: CV
作者: Sheng-Wei Zhang, Hsi-An Chen, Yan-Ting Liou, Chih-Hsuan Chen, Shih-Chen Tseng, Yu-Lun Liu
发布时间: 2026-10-19
arXiv: 2610.26851

中文摘要

将现有漫画改编为忠实于原著的连贯动画有价值但极具挑战。现有方法要么主要通过文本访问漫画——丢失角色和艺术风格，要么将页面直接输入视频生成模型——误解漫画结构并产生错误故事线。我们提出Manga2Animate——将生成每个阶段都锚定在源漫画上的多智能体框架。任务被分解为动画脚本和视觉故事板两种中间表示，每种由创作者智能体生成并由配对的审稿智能体对照源画面审查。通过特定表示的选择机制和双层反馈逐步细化后合成最终动画。大量实验和用户研究表明，Manga2Animate生成的动画比现有最先进方法更忠实于源漫画且镜头间一致性更高。

原文摘要

Adapting existing manga into coherent animation that stays faithful to the source is a valuable yet challenging task. Existing methods either access the manga mainly through text, losing its characters and art style, or feed manga pages directly into video generation models, which misinterpret the manga's structure and produce incorrect storylines. In this paper, we propose Manga2Animate, a multi-agent framework that grounds every stage of generation in the source manga. We decompose the task into two intermediate representations, an animation script and a visual storyboard. Each representation is produced by a creator agent and reviewed against the source panels by a paired reviewer agent. We tailor representation-specific selection and dual-level feedback to progressively refine both bef...

自动采集于 2026-10-21

#论文 #arXiv #CV #小凯