Knowledge Commons of Institute of Automation,CAS
Decoupled Representation Learning for Character Glyph Synthesis | |
Xiyan Liu1,2; Gaofeng Meng1,2,3; Jianlong Chang1,2; Ruiguang Hu4; Shiming Xiang1,2; Chunhong Pan1 | |
发表期刊 | IEEE Transactions on Multimedia |
ISSN | 1520-9210 |
2021 | |
卷号 | 2021期号:2021页码:1-13 |
通讯作者 | Meng, Gaofeng(gfmeng@nlpr.ia.ac.cn) |
摘要 | Character glyph synthesis is still an open challenging problem, which involves two related aspects, i.e., font style transfer and content consistency. In this paper, we propose a novel model named FontGAN, which integrates the character structure stylization, de-stylization and texture transfer into a unified framework. Specifically, we decouple character images into style representation and content representation, which offers fine-grained control of these two types of variables, thus improving the quality of the generated results. To effectively capture the style information, a style consistency module (SCM) is introduced. Technically, SCM exploits category-guided Kullback-Leibler divergence to explicitly model the style representation into different prior distributions. In this way, our model is capable of implementing transformations between multiple domains in one framework. In addition, we propose content prior module (CPM) to provide content prior for the model to guide the content encoding process and alleviates the problem of stroke deficiency during structure de-stylization. Benefiting from the idea of decoupling and regrouping, our FontGAN suffices to achieve many-to-many translation tasks for glyph structure. Experimental results demonstrate that the proposed FontGAN achieves the state-of-the-art performance in character glyph synthesis. |
关键词 | Character glyph synthesis Decoupled representation generative adversarial networks |
DOI | 10.1109/TMM.2021.3072449 |
收录类别 | SCI |
语种 | 英语 |
资助项目 | National Natural Science Foundation of China[61976208] ; National Natural Science Foundation of China[62071466] ; National Natural Science Foundation of China[62076242] |
项目资助者 | National Natural Science Foundation of China |
WOS研究方向 | Computer Science ; Telecommunications |
WOS类目 | Computer Science, Information Systems ; Computer Science, Software Engineering ; Telecommunications |
WOS记录号 | WOS:000778959200004 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
七大方向——子方向分类 | 文字识别与文档分析 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/46642 |
专题 | 多模态人工智能系统全国重点实验室_先进时空数据分析与学习 |
通讯作者 | Gaofeng Meng |
作者单位 | 1.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences 3.Centre for Artificial Intelligence and Robotics, HK Institute of Science & Innovation, Chinese Academy of Sciences 4.Beijing Aerospace Automatic Control Institute |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Xiyan Liu,Gaofeng Meng,Jianlong Chang,et al. Decoupled Representation Learning for Character Glyph Synthesis[J]. IEEE Transactions on Multimedia,2021,2021(2021):1-13. |
APA | Xiyan Liu,Gaofeng Meng,Jianlong Chang,Ruiguang Hu,Shiming Xiang,&Chunhong Pan.(2021).Decoupled Representation Learning for Character Glyph Synthesis.IEEE Transactions on Multimedia,2021(2021),1-13. |
MLA | Xiyan Liu,et al."Decoupled Representation Learning for Character Glyph Synthesis".IEEE Transactions on Multimedia 2021.2021(2021):1-13. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Decoupled_Representa(4588KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论