Filters








10 Hits in 4.2 sec

Auto-Encoder Guided GAN for Chinese Calligraphy Synthesis [article]

Pengyuan Lyu, Xiang Bai, Cong Yao, Zhen Zhu, Tengteng Huang, Wenyu Liu
2017 arXiv   pre-print
Besides, we also construct a large scale benchmark that contains various styles for Chinese calligraphy synthesis.  ...  In this paper, we investigate the Chinese calligraphy synthesis problem: synthesizing Chinese calligraphy images with specified style from standard font(eg. Hei font) images (Fig. 1(a)).  ...  For convenience, we call this dataset Chinese Calligraphy Synthesis-4(CCS-4). B.  ... 
arXiv:1706.08789v1 fatcat:5224avnk5jffxggjlk2u7sptp4

End-to-End Rubbing Restoration Using Generative Adversarial Networks [article]

Gongbo Sun, Zijie Zheng, Ming Zhang
2022 arXiv   pre-print
Rubbing restorations are significant for preserving world cultural history. In this paper, we propose the RubbingGAN model for restoring incomplete rubbing characters.  ...  We design the first generative adversarial network for rubbing restoration.  ...  The L(•) represents the reconstruction loss function for the auto-encoder.  ... 
arXiv:2205.03743v1 fatcat:c5un35y3h5ggzboqyn7daq64wu

GANwriting: Content-Conditioned Generation of Styled Handwritten Word Images [article]

Lei Kang, Pau Riba, Yaxing Wang, Marçal Rusiñol, Alicia Fornés, Mauricio Villegas
2020 arXiv   pre-print
Our generator is guided by three complementary learning objectives: to produce realistic images, to imitate a certain handwriting style and to convey a specific textual content.  ...  Lyu, P., Bai, X., Yao, C., Zhu, Z., Huang, T., Liu, W.: Auto-encoder guided GAN for Chinese calligraphy synthesis.  ...  Concerning the generation of handwritten text, such approaches have been mainly used for synthesising Chinese ideograms [30, 41, 6, 22, 44] and glyphs [2] .  ... 
arXiv:2003.02567v2 fatcat:ooztnppezraltfgdczankeryru

Editing Text in the Wild [article]

Liang Wu, Chengquan Zhang, Jiaming Liu, Junyu Han, Jingtuo Liu, Errui Ding, Xiang Bai
2019 arXiv   pre-print
We also conduct extensive experiments to validate the usefulness of our method in various real-world applications such as text image synthesis, augmented reality (AR) translation, information hiding, etc  ...  Xiang Bai by the National Program for Support of Top-notch Young Professionals and the Program for HUST Academic Frontier Youth Team 2017QYTD08.  ...  We sincerely thank Zhen Zhu and Tengteng Huang for their valuable discussions and continuous help to this paper.  ... 
arXiv:1908.03047v1 fatcat:skm7yrjuibaxbnfgwhpphkoidi

Separating Style and Content for Generalized Style Transfer [article]

Yexun Zhang, Ya Zhang, Wenbin Cai, Jie Chang
2018 arXiv   pre-print
For validation, we applied the proposed algorithm to the Chinese Typeface transfer problem.  ...  We here attempt to separate the representations for styles and contents, and propose a generalized style transfer network consisting of style encoder, content encoder, mixer and decoder.  ...  Lyu et. al proposed an auto-encoder guided GAN network (AEGN) which can synthesize calligraphy images with specified style from standard Chinese font images [16] .  ... 
arXiv:1711.06454v6 fatcat:prussibpmbaavnhcdsfq3hk5yy

A Unified Framework for Generalizable Style Transfer: Style and Content Separation [article]

Yexun Zhang, Ya Zhang, Wenbin Cai
2018 arXiv   pre-print
The encoders are expected to capture the underlying features for different styles and contents which is generalizable to new styles and contents.  ...  The overall framework consists of style encoder, content encoder, mixer and decoder.  ...  . • Auto-encoder guided GAN [23] : Auto-encoder guided GAN consists of two encoder-decoder networks, one for image transfer and another acting as an auto-encoder to guide the transfer to learn detailed  ... 
arXiv:1806.05173v1 fatcat:l636wzbrtbgghkunimobu7mfzy

Few-shot Compositional Font Generation with Dual Memory [article]

Junbum Cha, Sanghyuk Chun, Gayoung Lee, Bado Lee, Seonghyeon Kim, Hwalsuk Lee
2020 arXiv   pre-print
Generating a new font library is a very labor-intensive and time-consuming job for glyph-rich scripts.  ...  Acknowledgement We thank Clova OCR and Clova AI Research team for discussion and advice, especially Song Park for the internal review.  ...  Lyu, P., Bai, X., Yao, C., Zhu, Z., Huang, T., Liu, W.: Auto-encoder guided gan for chinese calligraphy synthesis. In: International Conference on Document Analysis and Recognition (2017) 1, 3 34.  ... 
arXiv:2005.10510v2 fatcat:cza3nrdvqjeehmm45he5m4cjg4

Table of contents

2019 2019 Chinese Control Conference (CCC)   unpublished
OUYANG Peilun, CAO Weihua, WU Min, GAN Chao, System Design for Electric-drive Rig in Complex Geological Drilling Process . . . . .  ...  MAO Chuwei, HUO Ju, ZHANG Zhanyu 4697 A Novel Shape Detection Method for Continuum Soft Manipulator Based on Cable Encoders . . . . . . . . . . . . . . . . . . . . . . . . .  ... 
doi:10.23919/chicc.2019.8866607 fatcat:bkwxxogrqvcmfpmqiek3xgnuoe

Annali di Ca' Foscari Annali di Ca' Foscari Serie orientale

Antonio Direttore, Rigopoulos
unpublished
of those that are likely to be absolutely transparent for the Chinese readership.  ...  Most of them are obviously meant for the non-Chinese reader and account for the transformation of the Chinese language in post-reform China, whereas others focus on the English lexicon and are therefore  ...  Weber believed that one of the most basic prerequisites for the modern capitalistic movements, is to make a rational system of capital accounting the standard for all large industrial enterprises that  ... 
fatcat:hcegtzfxebgzfpfvr3mdpekarm

Eating Potato Chips with Chopsticks: Nikkei Latin Americans Making Home, Shaping Family and Defining Selves [article]

(:Unkn) Unknown, University, My, Judith Goode
2020
For many, transnational migration is the only viable option for economic survival.  ...  Food categories therefore encode social events" (1971: x).  ...  This was true for me; Estella was my guiding light. When we met, I was struggling to find my way "in" so to speak.  ... 
doi:10.34944/dspace/1860 fatcat:bsjht6bzejbkhhqtvt4wtd7zwa