ABSTRACT
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.
Supplemental Material
Available for Download
Supplemental Material
- Samaneh Azadi, Matthew Fisher, Vladimir G Kim, Zhaowen Wang, Eli Shechtman, and Trevor Darrell. 2018. Multi-content gan for few-shot font style transfer. In CVPR. 7564--7573.Google Scholar
- Junbum Cha, Sanghyuk Chun, Gayoung Lee, Bado Lee, Seonghyeon Kim, and Hwalsuk Lee. 2020. Few-shot Compositional Font Generation with Dual Memory. arXiv:2005.10510 (2020).Google Scholar
- Tian Qi Chen and Mark Schmidt. 2016. Fast patch-based style transfer of arbitrary style. arXiv:1612.04337 (2016).Google Scholar
- Yunjey Choi, Minje Choi, Munyoung Kim, Jung-Woo Ha, Sunghun Kim, and Jaegul Choo. 2018. Stargan: Unified generative adversarial networks for multi-domain image-to-image translation. In CVPR. 8789--8797.Google Scholar
- Yunjey Choi, Youngjung Uh, Jaejun Yoo, and Jung-Woo Ha. 2020. Stargan v2: Diverse image synthesis for multiple domains. In IEEE/CVF Conference on Computer Vision and Pattern Recognition. 8188--8197.Google ScholarCross Ref
- Xueying Du, Jiangqin Wu, and Yang Xia. 2016. Bayesian relevance feedback based chinese calligraphy character synthesis. In ICME. IEEE, 1--6.Google Scholar
- Yue Gao, Yuan Guo, Zhouhui Lian, Yingmin Tang, and Jianguo Xiao. 2019. Artistic glyph image synthesis via one-stage few-shot learning. ACM TOG, Vol. 38, 6 (2019), 1--12. Google ScholarDigital Library
- Y. Gao and J. Wu. 2020. GAN-Based Unpaired Chinese Character Image Translation via Skeleton Transformation and Stroke Rendering. Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34, 1 (2020), 646--653.Google Scholar
- Leon A Gatys, Alexander S Ecker, and Matthias Bethge. 2016. Image style transfer using convolutional neural networks. In CVPR. 2414--2423.Google Scholar
- Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. In NIPS. 2672--2680. Google ScholarDigital Library
- Arthur Gretton, Karsten Borgwardt, Malte Rasch, Bernhard Schölkopf, and Alex J Smola. 2007. A kernel method for the two-sample-problem. In NIPS. 513--520. Google ScholarDigital Library
- Xun Huang and Serge Belongie. 2017. Arbitrary style transfer in real-time with adaptive instance normalization. In ICCV. 1501--1510.Google Scholar
- Yaoxiong Huang, Mengchao He, Lianwen Jin, and Yongpan Wang. 2020. RD-GAN: Few/Zero-Shot Chinese Character Style Transfer via Radical Decomposition and Rendering. ECCV.Google Scholar
- Satoshi Iizuka, Edgar Simo-Serra, and Hiroshi Ishikawa. 2017. Globally and locally consistent image completion. ACM, Vol. 36, 4 (2017), 1--14. Google ScholarDigital Library
- Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, and Alexei A Efros. 2017. Image-to-image translation with conditional adversarial networks. In CVPR. 1125--1134.Google Scholar
- Yue Jiang, Zhouhui Lian, Yingmin Tang, and Jianguo Xiao. 2017. DCFont: an end-to-end deep Chinese font generation system. In SIGGRAPH Asia 2017 Technical Briefs. 1--4. Google ScholarDigital Library
- Justin Johnson, Alexandre Alahi, and Li Fei-Fei. 2016. Perceptual losses for real-time style transfer and super-resolution. In ECCV. Springer, 694--711.Google Scholar
- Tero Karras, Timo Aila, Samuli Laine, and Jaakko Lehtinen. 2017. Progressive growing of gans for improved quality, stability, and variation. arXiv:1710.10196 (2017).Google Scholar
- Tero Karras, Samuli Laine, and Timo Aila. 2019. A style-based generator architecture for generative adversarial networks. In CVPR. 4401--4410.Google Scholar
- Junho Kim, Minjae Kim, Hyeonwoo Kang, and Kwanghee Lee. 2019. U-gat-it: unsupervised generative attentional networks with adaptive layer-instance normalization for image-to-image translation. arXiv:1907.10830 (2019).Google Scholar
- Ming-Yu Liu, Thomas Breuel, and Jan Kautz. 2017. Unsupervised image-to-image translation networks. In NIPS. 700--708. Google ScholarDigital Library
- Ming-Yu Liu and Oncel Tuzel. 2016. Coupled generative adversarial networks. In NIPS. 469--477. Google ScholarDigital Library
- Jonathan Long, Evan Shelhamer, and Trevor Darrell. 2015. Fully convolutional networks for semantic segmentation. In CVPR. 3431--3440.Google Scholar
- Pengyuan Lyu, Xiang Bai, Cong Yao, Zhen Zhu, Tengteng Huang, and Wenyu Liu. 2017. Auto-encoder guided gan for chinese calligraphy synthesis. In ICDAR, Vol. 1. IEEE, 1095--1100.Google ScholarCross Ref
- Xudong Mao, Qing Li, Haoran Xie, Raymond YK Lau, Zhen Wang, and Stephen Paul Smolley. 2017. Least squares generative adversarial networks. In ICCV. 2794--2802.Google Scholar
- SC Martin Arjovsky and Leon Bottou. 2017. Wasserstein generative adversarial networks. In ICML .Google Scholar
- Hyeonwoo Noh, Seunghoon Hong, and Bohyung Han. 2015. Learning deconvolution network for semantic segmentation. In ICCV. 1520--1528. Google ScholarDigital Library
- Li S., Xie B., Wu J., Zhao Y., Liu C., and Ding Z. 2020. Simultaneous Semantic Alignment Network for Heterogeneous Domain Adaptation. In ACM MM . Google ScholarDigital Library
- Li S., Liu C., Xie B., Su L., Ding Z., and Huang G. 2019. Joint Adversarial Domain Adaptation. In ACM MM . Google ScholarDigital Library
- Li S., Liu C., Lin Q., Wen Q., Su L., Huang G., and Ding Z. 2021. Deep Residual Correction Network for Partial Domain Adaptation. IEEE TPAMI .Google Scholar
- Li S., Song S., Gao H., Ding Z., and Cheng W. 2018. Domain Invariant and Class Discriminative Feature Learning for Visual Domain Adaptation. In IEEE TIP .Google Scholar
- Danyang Sun, Tongzheng Ren, Chongxun Li, Hang Su, and Jun Zhu. 2017. Learning to write stylized chinese characters by reading a handful of examples. arXiv:1712.06424 (2017). Google ScholarDigital Library
- Donghui Sun, Qing Zhang, and Jun Yang. 2018. Pyramid Embedded Generative Adversarial Network for Automated Font Generation. In ICPR. IEEE, 976--981.Google Scholar
- Yuchen Tian. 2017. zi2zi: Master Chinese calligraphy with conditional adversarial networks. https://kaonashi-tyc. github.io/2017/04/06/zi2zi.html .Google Scholar
- Yu-ho Tseng and Youhe Zeng. 1993. A history of Chinese calligraphy .Chinese University Press.Google Scholar
- Dmitry Ulyanov, Vadim Lebedev, Andrea Vedaldi, and Victor S Lempitsky. 2016. Texture Networks: Feed-forward Synthesis of Textures and Stylized Images.. In ICML, Vol. 1. 4. Google ScholarDigital Library
- Paul Upchurch, Noah Snavely, and Kavita Bala. 2016. From A to Z: supervised transfer of style and content using deep neural network generators. arXiv:1603.02003 (2016).Google Scholar
- Ting-Chun Wang, Ming-Yu Liu, Jun-Yan Zhu, Andrew Tao, Jan Kautz, and Bryan Catanzaro. 2018. High-resolution image synthesis and semantic manipulation with conditional gans. In CVPR. 8798--8807.Google Scholar
- Chuan Wen, Jie Chang, Ya Zhang, Siheng Chen, Yanfeng Wang, Mei Han, and Qi Tian. 2019. Handwritten Chinese Font Generation with Collaborative Stroke Refinement. arXiv:1904.13268 (2019).Google Scholar
- Helena TF Wong and Horace HS Ip. 2000. Virtual brush: a model-based synthesis of Chinese calligraphy. Computers & Graphics, Vol. 24, 1 (2000), 99--113.Google ScholarCross Ref
- Shan-Jean Wu, Chih-Yuan Yang, and Jane Yung-jen Hsu. 2020. CalliGAN: Style and Structure-aware Chinese Calligraphy Character Generator. arXiv:2005.12500 (2020).Google Scholar
- Yingfei Wu, Yueting Zhuang, Yunhe Pan, and Jiangqin Wu. 2006. Web based chinese calligraphy learning with 3-d visualization method. In ICME. IEEE, 2073--2076.Google Scholar
- Songhua Xu, Hao Jiang, Tao Jin, Francis CM Lau, and Yunhe Pan. 2009. Automatic generation of chinese calligraphic writings with style imitation. IEEE INTELL SYST 2 (2009), 44--53. Google ScholarDigital Library
- Songhua Xu, Francis CM Lau, William K Cheung, and Yunhe Pan. 2005. Automatic generation of artistic Chinese calligraphy. IEEE INTELL SYST, Vol. 20, 3 (2005), 32--39. Google ScholarDigital Library
- Zili Yi, Hao Zhang, Ping Tan, and Minglun Gong. 2017. Dualgan: Unsupervised dual learning for image-to-image translation. In ICCV. 2849--2857.Google Scholar
- Jiahui Yu, Zhe Lin, Jimei Yang, Xiaohui Shen, Xin Lu, and Thomas S Huang. 2018. Generative image inpainting with contextual attention. In CVPR. 5505--5514.Google Scholar
- Jiahui Yu, Zhe Lin, Jimei Yang, Xiaohui Shen, Xin Lu, and Thomas S Huang. 2019. Free-form image inpainting with gated convolution. In ICCV. 4471--4480.Google Scholar
- Yexun Zhang, Ya Zhang, and Wenbin Cai. 2018. Separating style and content for generalized style transfer. In CVPR. 8447--8455.Google Scholar
- Bolei Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, and Antonio Torralba. 2016. Learning deep features for discriminative localization. In CVPR. 2921--2929.Google Scholar
- Jun-Yan Zhu, Philipp Krahenbühl, Eli Shechtman, and Alexei A Efros. 2016. Generative visual manipulation on the natural image manifold. In ECCV. Springer, 597--613.Google Scholar
- Jun-Yan Zhu, Taesung Park, Phillip Isola, and Alexei A Efros. 2017. Unpaired image-to-image translation using cycle-consistent adversarial networks. In ICCV. 2223--2232.Google Scholar
Index Terms
- ZiGAN: Fine-grained Chinese Calligraphy Font Generation via a Few-shot Style Transfer Approach
Recommendations
MLFont: Few-Shot Chinese Font Generation via Deep Meta-Learning
ICMR '21: Proceedings of the 2021 International Conference on Multimedia RetrievalThe automatic generation of Chinese fonts is challenging due to the large quantity and complex structure of Chinese characters. When there are insufficient reference samples for the target font, existing deep learning-based methods cannot avoid ...
Complete font generation of Chinese characters in personal handwriting style
IPCCC '15: Proceedings of the 2015 IEEE 34th International Performance Computing and Communications Conference (IPCCC)Since a complete Chinese font has typically several thousand or more Chinese characters and symbols, and most of them are much more complicated than English alphabets, it takes a lot of time and efforts for even professional font engineers to create a ...
Learning font-style space using style-guided discriminator for few-shot font generation
AbstractFont synthesis has become a quite active field of research since manual font design requires extensive domain tradecraft expertise that is labor intensive and time consuming, especially for languages with large number of characters such as ...
Highlights- We propose a font synthesis method by learning the similarity of same font and dissimilarity between different fonts.
- The proposed method learns font style in embedding space using a style-guided discriminator.
- The style-guided ...
Comments