Few-shot Font Generation with Localized Style Representations and Factorization

被引:0
|
作者
Park, Song [1 ,3 ]
Chun, Sanghyuk [2 ,3 ]
Cha, Junbum [3 ]
Lee, Bado [3 ]
Shim, Hyunjung [1 ]
机构
[1] Yonsei Univ, Sch Integrated Technol, Seoul, South Korea
[2] NAVER AI LAB, Seoul, South Korea
[3] NAVER CLOVA, Seoul, South Korea
基金
新加坡国家研究基金会;
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Automatic few-shot font generation is a practical and widely studied problem because manual designs are expensive and sensitive to the expertise of designers. Existing few-shot font generation methods aim to learn to disentangle the style and content element from a few reference glyphs, and mainly focus on a universal style representation for each font style. However, such approach limits the model in representing diverse local styles, and thus makes it unsuitable to the most complicated letter system, e.g., Chinese, whose characters consist of a varying number of components (often called "radical") with a highly complex structure. In this paper, we propose a novel font generation method by learning localized styles, namely component-wise style representations, instead of universal styles. The proposed style representations enable us to synthesize complex local details in text designs. However, learning component-wise styles solely from reference glyphs is infeasible in the few-shot font generation scenario, when a target script has a large number of components, e.g., over 200 for Chinese. To reduce the number of reference glyphs, we simplify component-wise styles by a product of component factor and style factor, inspired by low-rank matrix factorization. Thanks to the combination of strong representation and a compact factorization strategy, our method shows remarkably better few-shot font generation results (with only 8 reference glyph images) than other state-of-the-arts, without utilizing strong locality supervision, e.g., location of each component, skeleton, or strokes. The source code is available at https://github.com/clovaai/lffont.
引用
收藏
页码:2393 / 2402
页数:10
相关论文
共 50 条
  • [31] Style-Aware Radiology Report Generation with RadGraph and Few-Shot Prompting
    Yan, Benjamin
    Liu, Ruochen
    Kuo, David E.
    Adithan, Subathra
    Reis, Eduardo Pontes
    Kwak, Stephen
    Venugopal, Vasantha Kumar
    O'Connell, Chloe P.
    Saenz, Agustina
    Rajpurkar, Pranav
    Moor, Michael
    FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (EMNLP 2023), 2023, : 14676 - 14688
  • [32] XMP-Font: Self-Supervised Cross-Modality Pre-training for Few-Shot Font Generation
    Liu, Wei
    Liu, Fangyue
    Ding, Fei
    He, Qian
    Yi, Zili
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2022, : 7895 - 7904
  • [33] LEARNING COMPONENT-LEVEL AND INTER-CLASS GLYPH REPRESENTATION FOR FEW-SHOT FONT GENERATION
    Su, Yongliang
    Chen, Xu
    Wu, Lei
    Meng, Xiangxu
    2023 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, ICME, 2023, : 738 - 743
  • [34] LEARNING STYLE CORRELATION FOR ELABORATE FEW-SHOT CLASSIFICATION
    Kim, Junho
    Kim, Minsu
    Kim, Jung Uk
    Lee, Hong Joo
    Lee, Sangmin
    Hong, Joanna
    Ro, Yong Man
    2020 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2020, : 1791 - 1795
  • [35] Distinct Label Representations for Few-Shot Text Classification
    Ohashi, Sora
    Takayama, Junya
    Kajiwara, Tomoyuki
    Arase, Yuki
    ACL-IJCNLP 2021: THE 59TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS AND THE 11TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING, VOL 2, 2021, : 831 - 836
  • [36] Shaping Visual Representations With Attributes for Few-Shot Recognition
    Chen, Haoxing
    Li, Huaxiong
    Li, Yaohui
    Chen, Chunlin
    IEEE SIGNAL PROCESSING LETTERS, 2022, 29 : 1397 - 1401
  • [37] Interpretable Compositional Representations for Robust Few-Shot Generalization
    Mishra, Samarth
    Zhu, Pengkai
    Saligrama, Venkatesh
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2024, 46 (03) : 1496 - 1512
  • [38] Hierarchical compositional representations for few-shot action recognition
    Li, Changzhen
    Zhang, Jie
    Wu, Shuzhe
    Jin, Xin
    Shan, Shiguang
    COMPUTER VISION AND IMAGE UNDERSTANDING, 2024, 240
  • [39] Spoken Content and Voice Factorization for Few-shot Speaker Adaptation
    Wang, Tao
    Tao, Jianhua
    Fu, Ruibo
    Yi, Jiangyan
    Wen, Zhengqi
    Zhong, Rongxiu
    INTERSPEECH 2020, 2020, : 796 - 800
  • [40] A Closer Look at Few-shot Image Generation
    Zhao, Yunqing
    Ding, Henghui
    Huang, Houjing
    Cheung, Ngai-Man
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2022, : 9130 - 9140