# Generating Handwritten Chinese Characters using CycleGAN

arXiv: https://arxiv.org/abs/1801.08624 · HTML: https://mlsanity.com/paper/1801.08624/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jan 2018.

## Built on by (most cited first, 21 of 21)

- [DG-Font: Deformable Generative Networks for Unsupervised Font Generation](https://mlsanity.com/paper/2104.03064/) (2021)
- [TextStyleBrush: Transfer of Text Aesthetics from a Single Example](https://mlsanity.com/paper/2106.08385/) (2021)
- [Handwriting Transformers](https://mlsanity.com/paper/2104.03964/) (2021)
- [Content and Style Aware Generation of Text-line Images for Handwriting Recognition](https://mlsanity.com/paper/2204.05539/) (2022)
- [Disentangling Writer and Character Styles for Handwriting Generation](https://mlsanity.com/paper/2303.14736/) (2023)
- [Handwritten Text Generation from Visual Archetypes](https://mlsanity.com/paper/2303.15269/) (2023)
- [Underwater Light Field Retention : Neural Rendering for Underwater Imaging](https://mlsanity.com/paper/2203.11006/) (2022)
- [VATr++: Choose Your Words Wisely for Handwritten Text Generation](https://mlsanity.com/paper/2402.10798/) (2024)
- [Two Decades of Bengali Handwritten Digit Recognition: A Survey](https://mlsanity.com/paper/2206.02234/) (2022)
- [Generative Adversarial Networks for Image Super-Resolution: A Survey](https://mlsanity.com/paper/2204.13620/) (2022)
- [One-shot Compositional Data Generation for Low Resource Handwritten Text Recognition](https://mlsanity.com/paper/2105.05300/) (2021)
- [SE-GAN: Skeleton Enhanced GAN-based Model for Brush Handwriting Font Generation](https://mlsanity.com/paper/2204.10484/) (2022)
- [DGFont++: Robust Deformable Generative Networks for Unsupervised Font Generation](https://mlsanity.com/paper/2212.14742/) (2022)
- [TrInk: Ink Generation with Transformer Network](https://mlsanity.com/paper/2508.21098/) (2025)
- [PaCaNet: A Study on CycleGAN with Transfer Learning for Diversifying Fused Chinese Painting and Calligraphy](https://mlsanity.com/paper/2301.13082/) (2023)
- [MetaScript: Few-Shot Handwritten Chinese Content Generation via Generative Adversarial Networks](https://mlsanity.com/paper/2312.16251/) (2023)
- [Beyond Patches: Global-aware Autoregressive Model for Multimodal Few-Shot Font Generation](https://mlsanity.com/paper/2601.01593/) (2026)
- [End-to-End Rubbing Restoration Using Generative Adversarial Networks](https://mlsanity.com/paper/2205.03743/) (2022)
- [StrokeGAN+: Few-Shot Semi-Supervised Chinese Font Generation with Stroke Encoding](https://mlsanity.com/paper/2211.06198/) (2022)
- [SGCE-Font: Skeleton Guided Channel Expansion for Chinese Font Generation](https://mlsanity.com/paper/2211.14475/) (2022)
- [Design and Development of a Framework For Stroke-Based Handwritten Gujarati Font Generation](https://mlsanity.com/paper/2404.03277/) (2024)

## Abstract (arXiv)

Handwriting of Chinese has long been an important skill in East Asia. However, automatic generation of handwritten Chinese characters poses a great challenge due to the large number of characters. Various machine learning techniques have been used to recognize Chinese characters, but few works have studied the handwritten Chinese character generation problem, especially with unpaired training data. In this work, we formulate the Chinese handwritten character generation as a problem that learns a mapping from an existing printed font to a personalized handwritten style. We further propose DenseNet CycleGAN to generate Chinese handwritten characters. Our method is applied not only to commonly used Chinese characters but also to calligraphy work with aesthetic values. Furthermore, we propose content accuracy and style discrepancy as the evaluation metrics to assess the quality of the handwritten characters generated. We then use our proposed metrics to evaluate the generated characters from CASIA dataset as well as our newly introduced Lanting calligraphy dataset.