WriteViT: Handwritten Text Generation with Vision Transformer

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Nam, Dang Hoai, Khoa, Huynh Tong Dang, Duy, Vo Nguyen Le
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908370583158784
author Nam, Dang Hoai
Khoa, Huynh Tong Dang
Duy, Vo Nguyen Le
author_facet Nam, Dang Hoai
Khoa, Huynh Tong Dang
Duy, Vo Nguyen Le
contents Humans can quickly generalize handwriting styles from a single example by intuitively separating content from style. Machines, however, struggle with this task, especially in low-data settings, often missing subtle spatial and stylistic cues. Motivated by this gap, we introduce WriteViT, a one-shot handwritten text synthesis framework that incorporates Vision Transformers (ViT), a family of models that have shown strong performance across various computer vision tasks. WriteViT integrates a ViT-based Writer Identifier for extracting style embeddings, a multi-scale generator built with Transformer encoder-decoder blocks enhanced by conditional positional encoding (CPE), and a lightweight ViT-based recognizer. While previous methods typically rely on CNNs or CRNNs, our design leverages transformers in key components to better capture both fine-grained stroke details and higher-level style information. Although handwritten text synthesis has been widely explored, its application to Vietnamese -- a language rich in diacritics and complex typography -- remains limited. Experiments on Vietnamese and English datasets demonstrate that WriteViT produces high-quality, style-consistent handwriting while maintaining strong recognition performance in low-resource scenarios. These results highlight the promise of transformer-based designs for multilingual handwriting generation and efficient style adaptation.
format Preprint
id arxiv_https___arxiv_org_abs_2505_13235
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle WriteViT: Handwritten Text Generation with Vision Transformer
Nam, Dang Hoai
Khoa, Huynh Tong Dang
Duy, Vo Nguyen Le
Computer Vision and Pattern Recognition
Machine Learning
Humans can quickly generalize handwriting styles from a single example by intuitively separating content from style. Machines, however, struggle with this task, especially in low-data settings, often missing subtle spatial and stylistic cues. Motivated by this gap, we introduce WriteViT, a one-shot handwritten text synthesis framework that incorporates Vision Transformers (ViT), a family of models that have shown strong performance across various computer vision tasks. WriteViT integrates a ViT-based Writer Identifier for extracting style embeddings, a multi-scale generator built with Transformer encoder-decoder blocks enhanced by conditional positional encoding (CPE), and a lightweight ViT-based recognizer. While previous methods typically rely on CNNs or CRNNs, our design leverages transformers in key components to better capture both fine-grained stroke details and higher-level style information. Although handwritten text synthesis has been widely explored, its application to Vietnamese -- a language rich in diacritics and complex typography -- remains limited. Experiments on Vietnamese and English datasets demonstrate that WriteViT produces high-quality, style-consistent handwriting while maintaining strong recognition performance in low-resource scenarios. These results highlight the promise of transformer-based designs for multilingual handwriting generation and efficient style adaptation.
title WriteViT: Handwritten Text Generation with Vision Transformer
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2505.13235