Scholarlink

<p>The imitation of cursive handwriting is mainly limited to generating handwritten words or lines. Multiple synthetic outputs must be stitched together to create paragraphs or whole pages, whereby consistency and layout information are lost. To close this gap, we propose a method for imitating handwriting at the paragraph level that also works for unseen writing styles. Therefore, we introduce a modified latent diffusion model that enriches the encoder-decoder mechanism with specialized loss functions that explicitly preserve the style and content. We enhance the attention mechanism of the diffusion model with adaptive 2D positional encoding and the conditioning mechanism to work with two modalities simultaneously: a style image and the target text. This significantly improves the realism of the generated handwriting. We set a new benchmark in our comprehensive evaluation, achieving 61&#xa0;% mAP and 56&#xa0;% top-1 accuracy in style preservation, significantly outperforming the previous best method (37&#xa0;% mAP, 30&#xa0;% top-1). We are making our code publicly available for reproducibility, supporting research in this area and research into potential countermeasures: <a href="https://github.com/M4rt1nM4yr/paragraph_handwriting_imitation_ldm">https://github.com/M4rt1nM4yr/paragraph_handwriting_imitation_ldm</a></p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Zero-Shot Paragraph-level Handwriting Imitation with Latent Diffusion Models

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年7月12日

查看全文
  • Martin Mayr,
  • Marcel Dreier,
  • Florian Kordon,
  • Mathias Seuret,
  • Jochen Zöllner,
  • Fei Wu,
  • Andreas Maier,
  • Vincent Christlein

摘要

The imitation of cursive handwriting is mainly limited to generating handwritten words or lines. Multiple synthetic outputs must be stitched together to create paragraphs or whole pages, whereby consistency and layout information are lost. To close this gap, we propose a method for imitating handwriting at the paragraph level that also works for unseen writing styles. Therefore, we introduce a modified latent diffusion model that enriches the encoder-decoder mechanism with specialized loss functions that explicitly preserve the style and content. We enhance the attention mechanism of the diffusion model with adaptive 2D positional encoding and the conditioning mechanism to work with two modalities simultaneously: a style image and the target text. This significantly improves the realism of the generated handwriting. We set a new benchmark in our comprehensive evaluation, achieving 61 % mAP and 56 % top-1 accuracy in style preservation, significantly outperforming the previous best method (37 % mAP, 30 % top-1). We are making our code publicly available for reproducibility, supporting research in this area and research into potential countermeasures: https://github.com/M4rt1nM4yr/paragraph_handwriting_imitation_ldm