CalliGAN: Style and Structure-aware Chinese Calligraphy Character Generator

Wu, Shan; Yang, Chih‐Yuan; Hsu, Jane Yung-jen

doi:10.48550/arxiv.2005.12500

Cited by 11 publications

(18 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…EMD [48] and SA-VAE [32] use two different encoders to process content and style respectively. After absorbing the advantages of the above methods, CalliGAN [41] adds an extra component code of the character to train a conditional GAN, exploiting prior knowledge to maintain the structure information. While it needs a dictionary for each Chinese character to save its component code, this is a complicated preprocessing work.…”

Section: Chinese Font Generationmentioning

confidence: 99%

“…To better show our model's performance, we use the same datasets with CalliGAN [41]. The datasets could be downloaded from a Chinese calligraphy character website 1 , where there are more than 20 kinds of brush-written calligraphy sets belonging to different Chinese ancient experts.…”

Section: Experiments 41 Datasetsmentioning

confidence: 99%

“…To prove the advancement of our method in the field of few-shot font style transfer, we have extensively compared various methods. Six classic methods are used as the baselines, including zi2zi [34], pix2pix [15], U-GAT-IT [20], CycleGAN [51], StarGAN [4], Calli-GAN [41]. Among them, zi2zi, pix2pix and CalliGAN need paired data for training.…”

Section: Qualitative Evaluationmentioning

confidence: 99%

“…Zi2zi [34] is proposed based on the pix2pix framework, which results in good synthesizing performance in some specific font styles. On this basis, CalliGAN [41] further uses the prior information of Chinese character radicals to achieve better results. But this leads to a more complex and fragmented network structure.…”

Section: Introductionmentioning

confidence: 99%

“…In the meantime, we randomly sample and render 6000 unpaired images with font style Song which cover a large number of characters as input 𝑥 𝑟 .The images in this repository have various shapes depending on the character's shapes. We follow the preprocessing steps of CalliGAN[41], but the only difference is that we process the images into three-channel RGB images. So we get 256 × 256 × 3 images as our ground truth 𝑦.…”

mentioning

confidence: 99%

See 4 more Smart Citations

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

Han

2021

Proceedings of the 29th ACM International Conference on Multimedia

View full text Add to dashboard Cite

Chinese character style transfer is a very challenging problem because of the complexity of the glyph shapes or underlying structures and large numbers of existed characters, when comparing with English letters. Moreover, the handwriting of calligraphy masters has a more irregular stroke and is difficult to obtain in real-world scenarios. Recently, several GAN-based methods have been proposed for font synthesis, but some of them require numerous reference data and the other part of them have cumbersome preprocessing steps to divide the character into different parts to be learned and transferred separately. In this paper, we propose 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. To be specific, a few paired samples from different character styles are leveraged to attain fine-grained correlation between structures underlying different glyphs. To capture valuable style knowledge in target and strengthen the coarse-grained understanding of character content, we utilize multiple unpaired samples to align the feature distributions belonging to different character styles. By doing so, only a few target Chinese calligraphy characters are needed to generated expected style transferred characters. Experiments demonstrate that our method has a state-of-the-art generalization ability in few-shot Chinese character style transfer. CCS CONCEPTS• Computing methodologies → Image processing.

show abstract

Section: Chinese Font Generationmentioning

confidence: 99%

Section: Experiments 41 Datasetsmentioning

confidence: 99%

Section: Qualitative Evaluationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations

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

Han

2021

Proceedings of the 29th ACM International Conference on Multimedia

View full text Add to dashboard Cite

show abstract

Content and Style Aware Generation of Text-Line Images for Handwriting Recognition

Kang

Riba²,

Rusiñol³

et al. 2022

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

Handwritten Text Recognition has achieved an impressive performance in public benchmarks. However, due to the high inter-and intra-class variability between handwriting styles, such recognizers need to be trained using huge volumes of manually labeled training data. To alleviate this labor-consuming problem, synthetic data produced with TrueType fonts has been often used in the training loop to gain volume and augment the handwriting style variability. However, there is a significant style bias between synthetic and real data which hinders the improvement of recognition performance. To deal with such limitations, we propose a generative method for handwritten text-line images, which is conditioned on both visual appearance and textual content. Our method is able to produce long text-line samples with diverse handwriting styles. Once properly trained, our method can also be adapted to new target data by only accessing unlabeled text-line images to mimic handwritten styles and produce images with any textual content. Extensive experiments have been done on making use of the generated samples to boost Handwritten Text Recognition performance. Both qualitative and quantitative results demonstrate that the proposed approach outperforms the current state of the art.

show abstract

AGTGAN: Unpaired Image Translation for Photographic Ancient Character Generation

Huang

Yang

Dai

et al. 2022

Proceedings of the 30th ACM International Conference on Multimedia

View full text Add to dashboard Cite

The study of ancient writings has great value for archaeology and philology. Essential forms of material are photographic characters, but manual photographic character recognition is extremely timeconsuming and expertise-dependent. Automatic classification is therefore greatly desired. However, the current performance is limited due to the lack of annotated data. Data generation is an inexpensive but useful solution to data scarcity. Nevertheless, the diverse glyph shapes and complex background textures of photographic ancient characters make the generation task difficult, leading to unsatisfactory results of existing methods. To this end, we propose an unsupervised generative adversarial network called AGTGAN in this paper. By explicitly modeling global and local glyph shape style, followed by a stroke-aware texture transfer and an associate adversarial learning mechanism, our method can generate characters with diverse glyphs and realistic textures. We evaluate our method on photographic ancient character datasets, e.g., OBC306 and CSDD. Our method outperforms other state-of-the-art methods in terms of various metrics and performs much better in terms of the diversity and authenticity of generated samples. With our generated images, experiments on the largest photographic oracle bone character dataset show that our method can achieve a significant increase in classification accuracy, up to 16.34%. The source code is available at https://github.com/Hellomystery/AGTGAN.

show abstract

CalliGAN: Style and Structure-aware Chinese Calligraphy Character Generator

Cited by 11 publications

References 24 publications

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

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

Content and Style Aware Generation of Text-Line Images for Handwriting Recognition

AGTGAN: Unpaired Image Translation for Photographic Ancient Character Generation

Contact Info

Product

Resources

About