CalliMaster: Mastering Page-level Chinese Calligraphy via Layout-guided Spatial Planning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912964394614784 |
|---|---|
| author | Xu, Tianshuo Hong, Tiantian Chen, Zhifei Chao, Fei Chen, Ying-cong |
| author_facet | Xu, Tianshuo Hong, Tiantian Chen, Zhifei Chao, Fei Chen, Ying-cong |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_12482 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CalliMaster: Mastering Page-level Chinese Calligraphy via Layout-guided Spatial Planning Xu, Tianshuo Hong, Tiantian Chen, Zhifei Chao, Fei Chen, Ying-cong Computer Vision and Pattern Recognition 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. |
| title | CalliMaster: Mastering Page-level Chinese Calligraphy via Layout-guided Spatial Planning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.12482 |