Few-shot Font Generation with Localized Style Representations and Factorization

Abstract

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.

Cross-language font style transfer

“…Section 4.2 shows some hyperparameters that we used to train and test the models. In Section 4.3, we introduce four state-of-the-art models, EMD [12] DFS [13], LF-Font [19], and MX-Font [20] that we compared with our model. After that, we report the quantitative and qualitative results in Section 4.4.…”

“…To improve the quality of the generated images, [13] proposed the Deep Feature Similarity (DFS) architecture to leverage the feature similarity between the input content and style images to synthesize target images. Recently, researchers [9,19,20,[44][45][46] have made significant progress by exploiting the compositionality of compositional scripts. However, our experimental results indicate poor performance for the constructed multi-language dataset.…”

“…However, finetuning is computationally expensive and cannot be applied to some real-time systems. Most recent works [19,20] require component labels as an additional supervision. However, comparison with methods that need component labels is not suitable.…”

“…Second, these methods cannot be applied to the crosslanguage transfer because some languages -like English -do not have compositional characters. Nevertheless, we visually compared our method with two compositionalbased methods, namely, LF-Font [19] and MX-Font [20].…”

“…(1) A detailed ablation study including loss and hyperparameter analysis was added to the journal version. (2) In the journal version, we compare our study with two recent works [19,20]. (3) The conference version only included the "English2Chinese" experiment.…”