发表机构
Loopdesk Technologies LLP（Loopdesk 科技有限公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
Srijika通过重用OpenType布局并利用扩散模型重绘字形，为九种印度文字生成完整字体，解决了合字一致性问题，并提供了审计基准和负面结果目录。
AI 中文摘要
我们提出了Srijika，一个为九种婆罗米系文字生成可安装OpenType字体的系统：天城文、泰米尔文、孟加拉文、泰卢固文、卡纳达文、马拉雅拉姆文、古吉拉特文、古木基文和奥里亚文。Srijika并非从头生成字体，而是从具有完整整形功能的模板字体中重样式化字形轮廓。它在文档化的度量策略下保留模板的cmap和GSUB闭包及其GPOS数据，从而在构造上确保每个输出都是完整字体。这解决了印度文字字体生成的一个核心挑战：数百到数千个合字、半形式和元音符号变体必须在OpenType整形下保持相互一致。Srijika生成了66个TTF文件：57个精选预设和9个开放词汇展示字体。所有这些都通过了OpenType Sanitizer的验证，而HarfBuzz和CoreText在合字密集的探针上复现了模板的字形ID序列。一项覆盖80,915个字形和54,812个锚点的全闭包审计量化了度量变化。自然语言风格选择使用Lipika，这是一个涵盖约650个开放许可字体家族的检索索引。一个参考条件潜在扩散模型以所选风格重绘模板字形，随后进行内容门控、协调和整形簇验证，并在必要时回退到模板轮廓。我们与无学习基线进行了对比评估。在扩散训练家族留出集的SSIM门控上，模板复制在56个字体中的50个上优于生成。风格移动仅在内部同模型嵌入（其训练语料包含留出家族）下可测量，因此这些结果需谨慎解读。学习基线、独立风格度量和人类研究不在本报告范围内。我们的贡献包括布局重用公式和流水线、其九种文字的审计和基准，以及涵盖参考引导重样式化的失败条件、目标选择和数据结构限制的负面结果目录。
英文摘要
We present Srijika, a system for producing installable OpenType fonts for nine Brahmic scripts: Devanagari, Tamil, Bengali, Telugu, Kannada, Malayalam, Gujarati, Gurmukhi, and Odia. Rather than generating fonts from scratch, Srijika restyles glyph outlines from shaping-complete template fonts. It preserves the template's cmap and GSUB closure and its GPOS data under a documented metric policy, making every output a complete font by construction. This addresses a central challenge of Indic font generation: hundreds to thousands of conjuncts, half forms, and matra variants must remain mutually consistent under OpenType shaping. Srijika produces 66 TTFs: 57 curated presets and nine open-vocabulary showcase fonts. All pass the OpenType Sanitizer, while HarfBuzz and CoreText reproduce the template glyph-ID sequences on conjunct-heavy probes. A full-closure audit covering 80,915 glyphs and 54,812 anchors quantifies metric changes. Natural-language style selection uses Lipika, a retrieval index over approximately 650 open-license font families. A reference-conditioned latent diffusion model redraws template glyphs in the selected style, followed by content gating, harmonization, and shaped-cluster verification with fallback to template outlines. We evaluate against no-learning baselines. On diffusion-training-family-held-out SSIM gates, template copying outperforms generation on 50 of 56 faces. Style movement is measurable only with an internal same-model embedding whose training corpus includes the held-out families, so these results require caution. A learned baseline, independent style metric, and human study are outside this report's scope. Our contributions are the layout-reusing formulation and pipeline, its nine-script audit and benchmark, and a negative-results catalogue covering failed conditioning, objective choices, and data-hull limits of reference-guided restyling.
