• Corpus ID: 218889643

CalliGAN: Style and Structure-aware Chinese Calligraphy Character Generator

@article{Wu2020CalliGANSA,
  title={CalliGAN: Style and Structure-aware Chinese Calligraphy Character Generator},
  author={Shan Jean Wu and Chih-Yuan Yang and Jane Yung-jen Hsu},
  journal={ArXiv},
  year={2020},
  volume={abs/2005.12500}
}
Chinese calligraphy is the writing of Chinese characters as an art form performed with brushes so Chinese characters are rich of shapes and details. Recent studies show that Chinese characters can be generated through image-to-image translation for multiple styles using a single model. We propose a novel method of this approach by incorporating Chinese characters' component information into its model. We also propose an improved network to convert characters to their embedding space… 

An end-to-end model for chinese calligraphy generation

An end-to-end network for character generation based on specific calligraphy styles designed to transfer the style of characters, and a content supplement network designed to capture the details of stylish strokes is proposed.

ZiGAN: Fine-grained Chinese Calligraphy Font Generation via a Few-shot Style Transfer Approach

This paper proposes a simple but powerful end-to-end Chinese calligraphy font generation framework ZiGAN, which does not require any manual operation or redundant preprocessing to generate fine-grained target style characters with few-shot references and has a state-of-the-art generalization ability in few- shot Chinese character style transfer.

Learning to Compose Stylistic Calligraphy Artwork with Emotions

A novel cross-modal approach to generate stylistic and diverse Chinese calligraphy artwork driven by different emotions automatically via a novel modified Generative Adversarial Network (GAN) structure, which outperforms all baseline image translation models significantly for different emotional styles.

Components Regulated Generation of Handwritten Chinese Text-lines in Arbitrary Length

This work proposes a components regulated model named HCT-GAN to generate the entire lines of Chinese handwriting from text-line labels that additionally integrates a Chinese text encoder, a sequence recognition module, and a spatial perception module (SPM).

AGTGAN: Unpaired Image Translation for Photographic Ancient Character Generation

This paper proposes an unsupervised generative adversarial network called AGTGAN, which can generate characters with diverse glyphs and realistic textures and outperforms other state-of-the-art methods in terms of various metrics and performs much better interms of the diversity and authenticity of generated samples.

SGCE-Font: Skeleton Guided Channel Expansion for Chinese Font Generation

Numerical results show that the mode collapse issue suffered by the known CycleGAN can be effectively alleviated by equipping with the proposed SGCE module, and the CycleGAN equipped with SGCE outperforms the state-of-the-art models in terms of four important evaluation metrics and visualization quality.

StrokeGAN: Reducing Mode Collapse in Chinese Font Generation via Stroke Encoding

A one-bit stroke encoding to capture the key mode information of Chinese characters and then incorporate it into CycleGAN, a popular deep generative model for Chinese font generation, and introduces a stroke-encoding reconstruction loss imposed on the discriminator.

StrokeGAN+: Few-Shot Semi-Supervised Chinese Font Generation with Stroke Encoding

Experimental results show that the mode collapse issue can be effectively alleviated by the introduced one-bit stroke encoding and few-shot semi-supervised training scheme, and that the proposed model outperforms the state-of-the-art models in fourteen font generation tasks in terms of four important evaluation metrics and the quality of generated characters.

FontTransformer: Few-shot High-resolution Chinese Glyph Image Synthesis via Stacked Transformers

FontTransformer, a novel few-shot learning model for high-resolution Chinese glyph image synthesis by using stacked Transformers to avoid the accumulation of prediction errors and utilize the serial Transformer to enhance the quality of synthesized strokes is proposed.

JokerGAN: Memory-Efficient Model for Handwritten Text Generation with Text Line Awareness

A new method for handwritten text generation is proposed that uses generative adversarial networks with multi-class conditional batch normalization, which enables us to use character sequences with variable lengths as conditional input and outperforms the current state-of-the-art for handwrittenText generation.

References

SHOWING 1-10 OF 37 REFERENCES

Automatic generation of artistic chinese calligraphy

An intelligent system that can automatically create novel, aesthetically appealing Chinese calligraphy from a few training examples of existing calligraphic styles is proposed.

Auto-Encoder Guided GAN for Chinese Calligraphy Synthesis

This work treats the calligraphy synthesis problem as an image-to-image translation problem and proposes a deep neural network based model which can generate calligraphY images from standard font images directly.

Generating Handwritten Chinese Characters Using CycleGAN

This work forms the Chinese handwritten character generation as a problem that learns a mapping from an existing printed font to a personalized handwritten style and proposes DenseNet CycleGAN to generate Chinese handwritten characters.

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

A novel framework of Style-Aware Variational Auto-Encoder (SA-VAE), which disentangles the content-relevant and style-relevant components of a Chinese character feature with a novel intercross pair-wise optimization method and has a powerful one-shot/few-shot generalization ability.

An Intelligent System for Chinese Calligraphy

This work extracts strokes of existent calligraphy using a semi-automatic, two-phase mechanism, and develops an intelligent user interface to allow the user to provide input to the extraction process for the difficult cases such as those in highly random, cursive, or distorted styles.

SCFont: Structure-Guided Chinese Font Generation via Deep Stacked Networks

A structure-guided Chinese font generation system, SCFont, by using deep stacked networks to integrate the domain knowledge of Chinese characters with deep generative networks to ensure that high-quality glyphs with correct structures can be synthesized.

Handwritten Chinese Font Generation with Collaborative Stroke Refinement

  • Chuan WenYujie Pan Qi Tian
  • Computer Science
    2021 IEEE Winter Conference on Applications of Computer Vision (WACV)
  • 2021
The proposed model significantly outperforms the state-of-the-art methods under practical setting, i.e. with only 750 paired training samples, and is added on top of any method for font synthesis.

Automatic Generation of Chinese Calligraphic Writings with Style Imitation

An automatic algorithm can generate Chinese calligraphy by quantitatively representing the characteristics of personal handwriting acquired from learning examples.

Automatic generation of large-scale handwriting fonts via style learning

Using the proposed system, for the first time the practical handwriting font library in a user's personal style with arbitrarily large numbers of Chinese characters can be generated automatically.

DCFont: an end-to-end deep chinese font generation system

A novel deep neural network architecture is designed to solve the font feature reconstruction and handwriting synthesis problems through adversarial training, which requires fewer input data but obtains more realistic and high-quality synthesis results compared to other deep learning based approaches.