CalliMaster：通过布局引导的空间规划掌握页面级中文书法
CalliMaster: Mastering Page-level Chinese Calligraphy via Layout-guided Spatial Planning
AI总结：
本文提出CalliMaster框架，通过解耦空间规划与内容合成，解决页面级书法生成中精度与布局的平衡问题，支持可控生成与编辑，扩展至文物修复与鉴定。
摘要：
页面级书法合成需要在字形精度与布局构成之间取得平衡。现有字符模型缺乏空间上下文，而页面级方法往往牺牲笔触细节。本文提出CalliMaster，一个统一的可控生成与编辑框架，通过解耦空间规划与内容合成来解决这一冲突。受人类认知过程『计划在前，书写在后』的启发，我们引入粗到细的流程（文本→布局→图像）来处理页面级合成的组合复杂性。在单一多模态扩散变换器中，空间规划阶段首先预测字符边界框以建立全局空间布局。此中间布局随后作为几何提示用于内容合成阶段，同一网络利用流匹配渲染高保真的笔触。除了达到最先进的生成质量，这种解耦支持多样的下游能力。通过将布局视为可修改的约束，CalliMaster使用户能够调整或重新定位字符，同时模型自动和谐周围空旷空间和笔触力度。此外，我们展示了该框架可扩展至文物修复和鉴定，提供数字文化遗产的全面工具。
英文摘要：
Page-level calligraphy synthesis requires balancing glyph precision with layout composition. Existing character models lack spatial context, while page-level methods often compromise brushwork detail. In this paper, we present \textbf{CalliMaster}, a unified framework for controllable generation and editing that resolves this conflict by decoupling spatial planning from content synthesis. Inspired by the human cognitive process of ``planning before writing'', we introduce a coarse-to-fine pipeline \textbf{(Text $\rightarrow$ Layout $\rightarrow$ Image)} to tackle the combinatorial complexity of page-scale synthesis. Operating within a single Multimodal Diffusion Transformer, a spatial planning stage first predicts character bounding boxes to establish the global spatial arrangement. This intermediate layout then serves as a geometric prompt for the content synthesis stage, where the same network utilizes flow-matching to render high-fidelity brushwork. Beyond achieving state-of-the-art generation quality, this disentanglement supports versatile downstream capabilities. By treating the layout as a modifiable constraint, CalliMaster enables controllable semantic re-planning: users can resize or reposition characters while the model automatically harmonizes the surrounding void space and brush momentum. Furthermore, we demonstrate the framework's extensibility to artifact restoration and forensic analysis, providing a comprehensive tool for digital cultural heritage.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
