FW-GAN: Frequency-Driven Handwriting Synthesis with Wave-Modulated MLP Generator
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914011477442560 |
|---|---|
| author | Khoa, Huynh Tong Dang Nam, Dang Hoai Duy, Vo Nguyen Le |
| author_facet | Khoa, Huynh Tong Dang Nam, Dang Hoai Duy, Vo Nguyen Le |
| contents | Labeled handwriting data is often scarce, limiting the effectiveness of recognition systems that require diverse, style-consistent training samples. Handwriting synthesis offers a promising solution by generating artificial data to augment training. However, current methods face two major limitations. First, most are built on conventional convolutional architectures, which struggle to model long-range dependencies and complex stroke patterns. Second, they largely ignore the crucial role of frequency information, which is essential for capturing fine-grained stylistic and structural details in handwriting. To address these challenges, we propose FW-GAN, a one-shot handwriting synthesis framework that generates realistic, writer-consistent text from a single example. Our generator integrates a phase-aware Wave-MLP to better capture spatial relationships while preserving subtle stylistic cues. We further introduce a frequency-guided discriminator that leverages high-frequency components to enhance the authenticity detection of generated samples. Additionally, we introduce a novel Frequency Distribution Loss that aligns the frequency characteristics of synthetic and real handwriting, thereby enhancing visual fidelity. Experiments on Vietnamese and English handwriting datasets demonstrate that FW-GAN generates high-quality, style-consistent handwriting, making it a valuable tool for augmenting data in low-resource handwriting recognition (HTR) pipelines. Official implementation is available at https://github.com/DAIR-Group/FW-GAN |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_21040 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FW-GAN: Frequency-Driven Handwriting Synthesis with Wave-Modulated MLP Generator Khoa, Huynh Tong Dang Nam, Dang Hoai Duy, Vo Nguyen Le Computer Vision and Pattern Recognition Machine Learning Labeled handwriting data is often scarce, limiting the effectiveness of recognition systems that require diverse, style-consistent training samples. Handwriting synthesis offers a promising solution by generating artificial data to augment training. However, current methods face two major limitations. First, most are built on conventional convolutional architectures, which struggle to model long-range dependencies and complex stroke patterns. Second, they largely ignore the crucial role of frequency information, which is essential for capturing fine-grained stylistic and structural details in handwriting. To address these challenges, we propose FW-GAN, a one-shot handwriting synthesis framework that generates realistic, writer-consistent text from a single example. Our generator integrates a phase-aware Wave-MLP to better capture spatial relationships while preserving subtle stylistic cues. We further introduce a frequency-guided discriminator that leverages high-frequency components to enhance the authenticity detection of generated samples. Additionally, we introduce a novel Frequency Distribution Loss that aligns the frequency characteristics of synthetic and real handwriting, thereby enhancing visual fidelity. Experiments on Vietnamese and English handwriting datasets demonstrate that FW-GAN generates high-quality, style-consistent handwriting, making it a valuable tool for augmenting data in low-resource handwriting recognition (HTR) pipelines. Official implementation is available at https://github.com/DAIR-Group/FW-GAN |
| title | FW-GAN: Frequency-Driven Handwriting Synthesis with Wave-Modulated MLP Generator |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2508.21040 |