让手写生成模型在未见字形下仍能真实还原书写风格。
DNA: Dual-branch Network with Adaptation for Open-Set Online Handwriting Generation
- 双分支结构分别学习书写风格与字符结构细节
- 在未见过的汉字上实现高保真手写生成
- 适合需要灵活生成新字形的应用场景
在线手写生成（OHG）通过合成多样且类人手写的样本，提升手写识别模型性能。然而，现有方法在生成未见字符时表现不佳，尤其在汉字等基于字形的语言中尤为明显，限制了其实际应用。本文提出双分支自适应网络（DNA），用于处理训练中未见过的书写者风格和测试时未见字符的生成任务。该模型包含自适应风格分支和自适应内容分支：风格分支学习笔画方向、间距、位置和连贯性等特征以生成逼真手写；内容分支通过局部编码器提取结构信息、全局编码器提取纹理细节，实现对未见字符的有效泛化。大量实验表明，所提DNA模型在未见手写生成场景下表现优异，达到当前最优水平。
原文摘要 · Abstract (English)
Online handwriting generation (OHG) enhances handwriting recognition models by synthesizing diverse, human-like samples. However, existing OHG methods struggle to generate unseen characters, particularly in glyph-based languages like Chinese, limiting their real-world applicability. In this paper, we introduce our method for OHG, where the writer's style and the characters generated during testing are unseen during training. To tackle this challenge, we propose a Dual-branch Network with Adaptation (DNA), which comprises an adaptive style branch and an adaptive content branch. The style branch learns stroke attributes such as writing direction, spacing, placement, and flow to generate realistic handwriting. Meanwhile, the content branch is designed to generalize effectively to unseen characters by decomposing character content into structural information and texture details, extracted via local and global encoders, respectively. Extensive experiments demonstrate that our DNA model is well-suited for the unseen OHG setting, achieving state-of-the-art performance.
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。