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

Mayr M, Dreier MN, Kordon F, Seuret M, Zöllner J, Wu F, Maier A, Christlein V (2025)

Publication Type: Journal article

Publication year: 2025

Journal

DOI: 10.1007/s11263-025-02525-0

Abstract

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

Authors with CRIS profile

Involved external institutions

Planet AI GmbH Germany (DE) University of Chinese Academy of Sciences China (CN)

How to cite

APA:

Mayr, M., Dreier, M.N., Kordon, F., Seuret, M., Zöllner, J., Wu, F.,... Christlein, V. (2025). Zero-Shot Paragraph-level Handwriting Imitation with Latent Diffusion Models. International Journal of Computer Vision. https://doi.org/10.1007/s11263-025-02525-0

MLA:

Mayr, Martin, et al. "Zero-Shot Paragraph-level Handwriting Imitation with Latent Diffusion Models." International Journal of Computer Vision (2025).

BibTeX: Download