Training machines to synthesize diverse handwritings is an intriguing task. Recently, RNN-based methods have been proposed to generate stylized online Chinese characters. However, these methods mainly focus on capturing a person's overall writing style, neglecting subtle style inconsistencies between characters written by the same person. For example, while a person's handwriting typically exhibits general uniformity (e.g., glyph slant and aspect ratios), there are still small style variations in finer details (e.g., stroke length and curvature) of characters. In light of this, we propose to disentangle the style representations at both writer and character levels from individual handwritings to synthesize realistic stylized online handwritten characters. Specifically, we present the style-disentangled Transformer (SDT), which employs two complementary contrastive objectives to extract the style commonalities of reference samples and capture the detailed style patterns of each sample, respectively. Extensive experiments on various language scripts demonstrate the effectiveness of SDT. Notably, our empirical findings reveal that the two learned style representations provide information at different frequency magnitudes, underscoring the importance of separate style extraction. Our source code is public at: https://github.com/dailenson/SDT.

翻译：训练机器合成多样化手写体是一项引人入胜的任务。近年来，基于循环神经网络的方法已被提出用于生成风格化的在线中文字符。然而，这些方法主要侧重于捕捉个人的整体书写风格，忽略了同一人书写字符间存在的细微风格不一致性。例如，尽管个人手写通常表现出整体一致性（如字形倾斜度和宽高比），但在字符的细微细节（如笔画长度和曲率）上仍存在小幅度风格变化。有鉴于此，我们提出从个人手写中解耦写作风格与字符风格表征，以合成逼真的风格化在线手写字符。具体而言，我们提出了风格解耦Transformer（SDT），它采用两种互补的对比学习目标，分别提取参考样本的风格共性并捕捉每个样本的详细风格模式。在不同语言脚本上的大量实验验证了SDT的有效性。值得注意的是，我们的实证发现表明，所学的两种风格表征提供了不同频率幅度的信息，强调了分离风格提取的重要性。我们的源代码已公开于：https://github.com/dailenson/SDT。