{"ID":2877311,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.21040","arxiv_id":"2508.21040","title":"FW-GAN: Frequency-Driven Handwriting Synthesis with Wave-Modulated MLP Generator","abstract":"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","short_abstract":"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 b...","url_abs":"https://arxiv.org/abs/2508.21040","url_pdf":"https://arxiv.org/pdf/2508.21040v1","authors":"[\"Huynh Tong Dang Khoa\",\"Dang Hoai Nam\",\"Vo Nguyen Le Duy\"]","published":"2025-08-28T17:44:52Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.LG\"]","methods":"[\"Generative Adversarial Network\"]","has_code":false,"code_links":[{"ID":610366,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2877311,"paper_url":"https://arxiv.org/abs/2508.21040","paper_title":"FW-GAN: Frequency-Driven Handwriting Synthesis with Wave-Modulated MLP Generator","repo_url":"https://github.com/DAIR-Group/FW-GAN","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}