Few-shot Font Generation with Weakly Supervised Localized Representations

12/22/2021
by   Song Park, et al.
0

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.

READ FULL TEXT

page 5

page 6

page 7

page 8

page 11

page 13

page 15

page 16

research
09/23/2020

Few-shot Font Generation with Localized Style Representations and Factorization

Automatic few-shot font generation is in high demand because manual desi...
research
04/02/2021

Multiple Heads are Better than One: Few-shot Font Generation with Multiple Localized Experts

A few-shot font generation (FFG) method has to satisfy two objectives: t...
research
09/02/2023

Few shot font generation via transferring similarity guided global style and quantization local style

Automatic few-shot font generation (AFFG), aiming at generating new font...
research
05/21/2020

Few-shot Compositional Font Generation with Dual Memory

Generating a new font library is a very labor-intensive and time-consumi...
research
04/11/2022

XMP-Font: Self-Supervised Cross-Modality Pre-training for Few-Shot Font Generation

Generating a new font library is a very labor-intensive and time-consumi...
research
08/27/2023

VQ-Font: Few-Shot Font Generation with Structure-Aware Enhancement and Quantization

Few-shot font generation is challenging, as it needs to capture the fine...
research
05/13/2022

FontNet: Closing the gap to font designer performance in font synthesis

Font synthesis has been a very active topic in recent years because manu...

Please sign up or login with your details

Forgot password? Click here to reset