Few-Shot Compositional Font Generation with Dual Memory

Cha, Junbum; Chun, Sanghyuk; Lee, Ga-Young; Lee, Bado; Kim, Seonghyun; Lee, Hwalsuk

doi:10.1007/978-3-030-58529-7_43

Cited by 58 publications

(60 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to save the cost of multiple Chinese characters selection, several recent methods aim to generate new glyphs with few numbers style references. DMfont [2] disassembles Korean or Thai glyphs to stylize components and then reassembles them. But it cannot handle complex Chinese characters.…”

Section: Chinese Font Generationmentioning

confidence: 99%

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%

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

“…Our data driven approach to obtain a generative font space is most closely related to previous approaches of unsupervised learning of fonts [17] and recent systems based on Generative Adversarial Networks (GAN), e.g. [6,19,20,62,68]. Diferently from [17], which used a polyline representation of letters, we used a pixel based representation as the current study renders text only to a monitor up to a size of 40 pt.…”

Section: Parametric Adaptive Generative and Smart Fontsmentioning

confidence: 99%

“…Another recent approach for font generation employs GANs, see e.g. [6,19,20,62,68]. Even though this technique gives good results at the letter and word level, current implementations sufer from problems in alignment and kerning in continuous texts.…”

Section: Learning a Font Spacementioning

confidence: 99%

AdaptiFont: Increasing Individuals’ Reading Speed with a Generative Font Model and Bayesian Optimization

Kadner¹,

Keller²,

Rothkopf

2021

Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

show abstract

“…For example, when creating a new Korean font library; designers must manually create every single character per font style, where there are a total of 11,172 possible Korean characters (or at least 2,350 widely used characters), while maintaining a coherent font style [1]. For this reason, various font generation methods [2], [3], [4], [5], [6] have been investigated to address an automatic font generation problem, which generates a font with a coherent style of the given reference glyph images; the number of reference glyphs varies with the application scenario.…”

Section: Introductionmentioning

confidence: 99%

“…In this study, we addressed a practical font generation scenario: a few-shot font generation problem, in glyphrich language systems [5], [6], [7], [8], [9], [10], [11], [12],…”

Section: Introductionmentioning

confidence: 99%

Few-shot Font Generation with Weakly Supervised Localized Representations

Park¹,

Chun²,

Cha³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Automatic few-shot font generation aims to solve a well-defined, real-world problem because manual font designs are expensive and sensitive to the expertise of designers. Existing methods learn to disentangle style and content elements by developing a universal style representation for each font style. However, this approach limits the model in representing diverse local styles, because it is unsuitable for complicated letter systems, for example, 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 that learns localized styles, namely component-wise style representations, instead of universal styles. The proposed style representations enable the synthesis of complex local details in text designs. However, learning component-wise styles solely from a few reference glyphs is infeasible when a target script has a large number of components, for example, over 200 for Chinese. To reduce the number of required reference glyphs, we represent component-wise styles by a product of component and style factors, inspired by low-rank matrix factorization. Owing to the combination of strong representation and a compact factorization strategy, our method shows remarkably better few-shot font generation results (with only eight reference glyphs) than other state-of-the-art methods. Moreover, strong locality supervision, for example, location of each component, skeleton, or strokes, was not utilized. The source code is available at https://github.com/clovaai/lffont and https://github.com/clovaai/fewshot-font-generation.

show abstract

Few-Shot Compositional Font Generation with Dual Memory

Cited by 58 publications

References 26 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

AdaptiFont: Increasing Individuals’ Reading Speed with a Generative Font Model and Bayesian Optimization

Few-shot Font Generation with Weakly Supervised Localized Representations

Contact Info

Product

Resources

About