CalliMaster: Mastering Page-level Chinese Calligraphy via Layout-guided Spatial Planning

2026-03-12

AI Summary

This work addresses the challenge of page-level Chinese calligraphy generation, which requires simultaneous fidelity to fine glyph details and coherent global layout—a balance existing methods struggle to achieve. To this end, we propose CalliMaster, a novel framework that decouples spatial planning from content synthesis through a coarse-to-fine “text → layout → image” pipeline within a unified multimodal diffusion Transformer. The model first predicts character bounding boxes and then leverages this geometric layout as a conditioning prompt to synthesize high-fidelity calligraphic images. Crucially, the layout is treated as an editable constraint, enabling semantic reordering, scaling, and positional adjustments while automatically harmonizing negative space and brushstroke dynamics. Our approach achieves state-of-the-art generation quality and supports practical applications such as controllable editing, digital artifact restoration, and handwriting authentication.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

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.

Problem

• page-level calligraphy synthesis
• spatial planning
• layout composition
• brushwork detail
• character layout

Innovation

• layout-guided synthesis
• spatial planning
• Chinese calligraphy generation
• multimodal diffusion transformer
• controllable editing