Learning to Write Stylized Chinese Characters by Reading a Handful of Examples

2017/12/06 by Danyang Sun, Tongzheng Ren, Sun, Danyang +7 · 4 citations
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Handwritten Text Recognition Techniques #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Video Analysis and Summarization

paper · pdf · doi:10.48550/arxiv.1712.06424

openalex publication_date 2017/12/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Automatically writing stylized Chinese characters is an attractive yet challenging task due to its wide applicabilities. In this paper, we propose a novel framework named Style-Aware Variational Auto-Encoder (SA-VAE) to flexibly generate Chinese characters. Specifically, we propose to capture the different characteristics of a Chinese character by disentangling the latent features into content-related and style-related components. Considering of the complex shapes and structures, we incorporate the structure information as prior knowledge into our framework to guide the generation. Our framework shows a powerful one-shot/low-shot generalization ability by inferring the style component given a character with unseen style. To the best of our knowledge, this is the first attempt to learn to write new-style Chinese characters by observing only one or a few examples. Extensive experiments demonstrate its effectiveness in generating different stylized Chinese characters by fusing the feature vectors corresponding to different contents and styles, which is of significant importance in real-world applications.

Citations

• LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Learning Typographic Style
• Adversarial Feature Learning
• Densely Connected Convolutional Networks

Cited by

• DA-Font: Few-Shot Font Generation via Dual-Attention Hybrid Integration
• Automatic Generation of Chinese Handwriting via Fonts Style Representation Learning
• Handwritten Chinese Font Generation with Collaborative Stroke Refinement
• Multiform Fonts-to-Fonts Translation via Style and Content Disentangled Representations of Chinese Character

Related

• Disentangling Writer and Character Styles for Handwriting Generation
• Automatic Generation of Chinese Handwriting via Fonts Style Representation Learning
• FontGAN: A Unified Generative Framework for Chinese Character Stylization and De-stylization
• CalliGAN: Style and Structure-aware Chinese Calligraphy Character Generator
• Stroke-Based Autoencoders: Self-Supervised Learners for Efficient Zero-Shot Chinese Character Recognition