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

[2409.00786] Zero-Shot Paragraph-level Handwriting Imitation with Latent Diffusion Models Skip to main content Search Submit Donate Log in Computer Science > Computer Vision and Pattern Recognition arXiv:2409.00786 (cs) [Submitted on 1 Sep 2024 ( v1 ), last revised 13 Jul 2026 (this version, v2)] Title: Zero-Shot Paragraph-level Handwriting Imitation with Latent Diffusion Models Authors: Martin Mayr , Marcel Dreier , Florian Kordon , Mathias Seuret , Jochen Zöllner , Fei Wu , Andreas Maier , Vincent Christlein View PDF HTML (experimental) 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: this https URL Subjects: Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2409.00786 [cs.CV] (or arXiv:2409.00786v2 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2409.00786 Focus to learn more arXiv-issued DOI via DataCite Journal reference: Int. J. Comput. Vis. 133 (2025) 7054-7075 Related DOI : https://doi.org/10.1007/s11263-025-02525-0 Focus to learn more DOI(s) linking to related resources Submission history From: Martin Mayr [ view email ] [v1] Sun, 1 Sep 2024 17:33:31 UTC (11,635 KB) [v2] Mon, 13 Jul 2026 10:49:26 UTC (9,343 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Current browse context: cs.CV < prev | next > new | recent | 2024-09 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Zero-Shot Paragraph-level Handwriting Imitation with Latent Diffusion Models#670292
• The iReCheck project: using tablets and robots for personalised handwriting practice#284433
• Imperfection for Precision: Upcycling Imperfect Data for High-Precision Robotic Manipulation#1062559
• Towards Scalable Human-aligned Benchmark for Text-guided Image Editing#626783
• Difference-Aware Retrieval Policies for Imitation Learning#267643