Abstract
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: this https URL.
Abstract (translated)
训练机器生成多样化的手写字体是一个有趣的任务。最近,基于RNN的方法被提出用于生成精心修饰的在线中文字符。但是这些方法主要关注捕捉一个人的整体写作风格,忽略了相同作者笔下字符的微妙风格一致性。例如,尽管一个人的手写字体通常具有普遍一致性(例如字斜度和比例),但字符的 fine grained 风格差异仍然存在。鉴于这一点,我们建议从作者和字符级别的风格表示中分离出来,以合成实际修饰的在线手写字符。具体来说,我们提出了风格分离的Transformer(SDT),它使用两个互补的对比度目标分别提取参考样本的风格一致性,并捕捉每个样本的详细风格模式。针对各种语言脚本,进行了广泛的实验,证明了SDT的有效性。特别值得一提的是,我们的实证研究表明,两种学习的风格表示提供不同的频率幅度信息,突出了分开风格提取的重要性。我们的源代码公开在以下httpsURL。
URL
https://arxiv.org/abs/2303.14736