发表机构
Zhejiang University of Technology; Zhejiang Lab（浙江工业大学; 之江实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出多字符语义排版框架MSTypography，通过全局轮廓近似与局部语义细化，结合结构损失和OCR约束，平衡单词可读性与对象可识别性，在五种语言上超越现有方法。
AI 中文摘要
语义排版是一种设计技术，其中单词的视觉表示传达其语义含义，同时保持其可读性。现有的数字排版方法主要关注单字符场景。当扩展到多字符单词时，它们缺乏可读性约束且局部变形不足，因为在排版过程中多个字符之间的复杂结构难以保持。在本文中，我们提出了一种面向多字符场景的从全局到局部的排版框架。它在全局层面执行基于掩码的轮廓近似，在局部层面执行语义引导的细化，并在其间加入剔除步骤以提高效率。为了保持单词可读性，我们设计了结构损失（包括显式碰撞约束和隐式雅可比奇异值约束）以及用于字符级可读性的OCR约束。为了增强对象可识别性，我们利用具有扩散先验的语义引导，在保持字形结构完整性的同时，将字符字形推向目标概念。据我们所知，这是第一个有效平衡单词可读性和对象可识别性的多字符语义排版方法。在五种代表性语言（英语、中文、日语、韩语、阿拉伯语）上的评估表明，该方法优于最先进的方法。代码将开源。
英文摘要
Semantic typography is a design technique where the visual representation of a word conveys its semantic meaning, while maintaining its legibility. Existing digital typography methods mainly focus on single-character scenarios. They suffer from a lack of legibility constraints and insufficient local deformation when extended to multi-character words, as the intricate structures among multiple characters are hardly preserved during the typography process. In this paper, we propose a global-to-local typography framework for multi-character scenarios. It performs mask-driven silhouette approximation at the global level, while semantic-guided refinement at the local level, with a culling step in between to improve efficiency. To preserve word legibility, we designed structural losses (including explicit collision constraints and implicit Jacobian singular value constraints) and an OCR constraint for character-level readability. To enhance the object recognizability, we leverage semantic guidance with diffusion priors, which drives the character glyph toward the target concept while preserving its structural integrity. To the best of our knowledge, this is the first multi-character semantic typography method that effectively balances word legibility and object recognizability. Evaluations on five representative languages (English, Chinese, Japanese, Korean, Arabic) demonstrate superiority over SOTA methods. Codes will be open-sourced.
