Diffusion-Based Ukrainian Handwritten Text Generation with Cross-Domain Style Transfer

• URL: http://arxiv.org/abs/2605.27487v1
• Date: Tue, 26 May 2026 15:28:21 GMT
• Title: Diffusion-Based Ukrainian Handwritten Text Generation with Cross-Domain Style Transfer
• Abstract summary: We construct a Ukrainian handwritten word dataset of 126,177 images from 308 writers using connected-component segmentation, quality filtering, and targeted oversampling of underrepresented Ukrainian characters.<n>We retrain a MobileNetV2 triplet-loss style encoder with a CANINE-conditioned latent diffusion U-Net, testing direct transfer from Latin to Cyrillic.<n>We evaluate cross-domain style transfer in three settings: cross-lingual transfer from English samples, zero-shot transfer to an early 20th-century Ukrainian manuscript, and few-shot imitation of contemporary writers.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Handwritten text generation (HTG) conditioned on writer style has been widely studied for Latin scripts, but remains underexplored for low-resource and non-Latin writing systems, leaving open how well existing models generalise beyond the Latin domain. Cyrillic, particularly Ukrainian, lacks both large-scale writer-labeled datasets and empirical evidence of such generalisation. To address this gap, we construct a Ukrainian handwritten word dataset of 126,177 images from 308 writers using connected-component segmentation, quality filtering, and targeted oversampling of underrepresented Ukrainian characters. We retrain DiffusionPen, a MobileNetV2 triplet-loss style encoder with a CANINE-conditioned latent diffusion U-Net, on this dataset without architectural modification, testing direct transfer from Latin to Cyrillic. We evaluate cross-domain style transfer in three settings: cross-lingual transfer from IAM English samples, zero-shot transfer to an early 20th-century Ukrainian manuscript, and few-shot imitation of contemporary writers. The model produces legible, style-consistent word images, indicating that few-shot latent diffusion models generalize beyond the Latin-script domain. We release the dataset, trained models, and evaluation protocol as a reproducible benchmark for writer-aware Cyrillic HTG, providing a foundation for extending stylized HTG to other underrepresented writing systems.

Related papers

• "Înţelegi Româneşte?'' A Recipe for Romanian Vision-Language Models [7.120569645707792]
  We present a systematic study of building a language-specific Vision-Language Models (VLMs) for Romanian.<n>We translate established English VLM training and evaluation corpora into Romanian, applying machine translation to textual annotations and to in-image text.<n>Using this data, we train and ablate a series of VLMs to isolate the contribution of vision backbones of varying scale and pretraining.<n>We also curate HoraVQA, a culturally native evaluation set grounded in Romanian everyday scenes.
  arXiv  Detail & Related papers  (2026-05-29T15:04:20Z)
• TextLDM: Language Modeling with Continuous Latent Diffusion [89.69255520673248]
  Diffusion Transformers (DiT) trained with flow matching in a VAE latent space have unified visual generation across images and videos.<n>We propose TextLDM, which transfers the visual latent diffusion recipe to text generation with minimal architectural modification.
  arXiv  Detail & Related papers  (2026-05-08T13:54:34Z)
• Bilingual Text-to-Motion Generation: A New Benchmark and Baselines [52.71312720094036]
  We introduce BiHumanML3D, the first bilingual text-to-motion benchmark, constructed via LLM-assisted annotation and rigorous manual correction.<n>We also propose a simple yet effective baseline, Bilingual Motion Diffusion synthesis (BiMD), featuring Cross-Lingual Alignment (CLA)<n>BiMD with CLA achieves an FID of 0.045 vs. 0.169 and R@3 of 82.8% vs. 80.8%, significantly outperforms monolingual diffusion models and translation baselines on BiHumanML3D.
  arXiv  Detail & Related papers  (2026-03-26T08:48:27Z)
• A Comprehensive Benchmark of Language Models on Unicode and Romanized Sinhala [0.2864713389096699]
  This paper presents a benchmark of modern Language Models (LMs) on a diverse corpus of Unicode and Romanized Sinhala.<n>We evaluate open-source models using perplexity, a measure of how well a model predicts a text, and leading closed-source models.
  arXiv  Detail & Related papers  (2026-01-21T12:58:46Z)
• Capturing Style in Author and Document Representation [4.323709559692927]
  We propose a new architecture that learns embeddings for both authors and documents with a stylistic constraint.<n>We evaluate our method on three datasets: a literary corpus extracted from the Gutenberg Project, the Blog Authorship and IMDb62.
  arXiv  Detail & Related papers  (2024-07-18T10:01:09Z)
• Exploring the Role of Transliteration in In-Context Learning for Low-resource Languages Written in Non-Latin Scripts [50.40191599304911]
  We investigate whether transliteration is also effective in improving LLMs' performance for low-resource languages written in non-Latin scripts. We propose three prompt templates, where the target-language text is represented in (1) its original script, (2) Latin script, or (3) both. Our findings show that the effectiveness of transliteration varies by task type and model size.
  arXiv  Detail & Related papers  (2024-07-02T14:51:20Z)
• Lost in Translation, Found in Spans: Identifying Claims in Multilingual Social Media [40.26888469822391]
  Claim span identification (CSI) is an important step in fact-checking pipelines. Despite its importance to journalists and human fact-checkers, it remains a severely understudied problem. We create a novel dataset, X-CLAIM, consisting of 7K real-world claims collected from numerous social media platforms in five Indian languages and English.
  arXiv  Detail & Related papers  (2023-10-27T15:28:12Z)
• PART: Pre-trained Authorship Representation Transformer [52.623051272843426]
  Authors writing documents imprint identifying information within their texts.<n>Previous works use hand-crafted features or classification tasks to train their authorship models.<n>We propose a contrastively trained model fit to learn textbfauthorship embeddings instead of semantics.
  arXiv  Detail & Related papers  (2022-09-30T11:08:39Z)
• StoryTrans: Non-Parallel Story Author-Style Transfer with Discourse Representations and Content Enhancing [73.81778485157234]
  Long texts usually involve more complicated author linguistic preferences such as discourse structures than sentences. We formulate the task of non-parallel story author-style transfer, which requires transferring an input story into a specified author style. We use an additional training objective to disentangle stylistic features from the learned discourse representation to prevent the model from degenerating to an auto-encoder.
  arXiv  Detail & Related papers  (2022-08-29T08:47:49Z)
• A Simple Multi-Modality Transfer Learning Baseline for Sign Language Translation [54.29679610921429]
  Existing sign language datasets contain only about 10K-20K pairs of sign videos, gloss annotations and texts. Data is thus a bottleneck for training effective sign language translation models. This simple baseline surpasses the previous state-of-the-art results on two sign language translation benchmarks.
  arXiv  Detail & Related papers  (2022-03-08T18:59:56Z)
• Phonetic and Visual Priors for Decipherment of Informal Romanization [37.77170643560608]
  We propose a noisy-channel WFST cascade model for deciphering the original non-Latin script from observed romanized text. We train our model directly on romanized data from two languages: Egyptian Arabic and Russian. We demonstrate that adding inductive bias through phonetic and visual priors on character mappings substantially improves the model's performance on both languages.
  arXiv  Detail & Related papers  (2020-05-05T21:57:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.