用笔画建模生成可缩放中文字符，支持创意设计与新字创作。
Stroke Modeling Enables Vectorized Character Generation with Large Vectorized Glyph Model
- 通过预测笔画嵌入生成完整汉字，模仿语言模型序列生成逻辑。
- 在90万笔画数据上训练，能生成语义流畅的词句及未见诗文。
- 适合字体设计、艺术创作与AI辅助汉字生成研究者使用。
矢量字形因其可缩放性和灵活性，广泛应用于海报设计、网络动画和艺术展示等领域。在字体学中，字形常被视为由有序笔画构成的特殊序列。这一概念延伸至大语言模型（LLM）的词元序列预测能力，使基于笔画建模的矢量字符生成成为可能。本文提出一种新型大规模矢量字形模型（LVGM），通过预测下一个笔画嵌入来生成矢量中文字符。首先将笔画编码为离散潜在变量——笔画嵌入；随后利用微调后的DeepSeek LLM进行训练，以预测下一个笔画嵌入。在仅提供少量笔画的情况下，该模型可生成完整字符、语义优美的词语乃至未见过的诗句，全部以矢量形式呈现。此外，我们发布了包含907,267个样本的新大型中文SVG数据集，专为动态矢量字形生成而构建。实验表明，模型在不同数据规模下表现出良好的扩展性。专家与相关人士对生成结果进行了验证，确认其质量可靠。
原文摘要 · Abstract (English)
Vectorized glyphs are widely used in poster design, network animation, art display, and various other fields due to their scalability and flexibility. In typography, they are often seen as special sequences composed of ordered strokes. This concept extends to the token sequence prediction abilities of large language models (LLMs), enabling vectorized character generation through stroke modeling. In this paper, we propose a novel Large Vectorized Glyph Model (LVGM) designed to generate vectorized Chinese glyphs by predicting the next stroke. Initially, we encode strokes into discrete latent variables called stroke embeddings. Subsequently, we train our LVGM via fine-tuning DeepSeek LLM by predicting the next stroke embedding. With limited strokes given, it can generate complete characters, semantically elegant words, and even unseen verses in vectorized form. Moreover, we release a new large-scale Chinese SVG dataset containing 907,267 samples based on strokes for dynamically vectorized glyph generation. Experimental results show that our model has scaling behaviors on data scales. Our generated vectorized glyphs have been validated by experts and relevant individuals.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。