# Handwritten Chinese Font Generation with Collaborative Stroke Refinement

arXiv: https://arxiv.org/abs/1904.13268 · HTML: https://mlsanity.com/paper/1904.13268/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Apr 2019.

## Built on by (most cited first, 8 of 8)

- [Few-Shot Font Generation by Learning Fine-Grained Local Styles](https://mlsanity.com/paper/2205.09965/) (2022)
- [ZiGAN: Fine-grained Chinese Calligraphy Font Generation via a Few-shot Style Transfer Approach](https://mlsanity.com/paper/2108.03596/) (2021)
- [SE-GAN: Skeleton Enhanced GAN-based Model for Brush Handwriting Font Generation](https://mlsanity.com/paper/2204.10484/) (2022)
- [VQ-Font: Few-Shot Font Generation with Structure-Aware Enhancement and Quantization](https://mlsanity.com/paper/2308.14018/) (2023)
- [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)
- [InkDiffuser: High-Fidelity One-shot Chinese Calligraphy via Differentiable Morphological Optimization](https://mlsanity.com/paper/2605.05865/) (2026)

## Abstract (arXiv)

Automatic character generation is an appealing solution for new typeface design, especially for Chinese typefaces including over 3700 most commonly-used characters. This task has two main pain points: (i) handwritten characters are usually associated with thin strokes of few information and complex structure which are error prone during deformation; (ii) thousands of characters with various shapes are needed to synthesize based on a few manually designed characters. To solve those issues, we propose a novel convolutional-neural-network-based model with three main techniques: collaborative stroke refinement, using collaborative training strategy to recover the missing or broken strokes; online zoom-augmentation, taking the advantage of the content-reuse phenomenon to reduce the size of training set; and adaptive pre-deformation, standardizing and aligning the characters. The proposed model needs only 750 paired training samples; no pre-trained network, extra dataset resource or labels is needed. Experimental results show that the proposed method significantly outperforms the state-of-the-art methods under the practical restriction on handwritten font synthesis.