SVG Vector Font Generation for Chinese Characters with Transformer
Haruka Aoki, Kiyoharu Aizawa

TL;DR
This paper introduces a novel Transformer-based network architecture that automatically generates Chinese vector fonts from minimal references, overcoming the complexity of Chinese characters and eliminating the need for differentiable rendering.
Contribution
The study presents the first successful method for automatic Chinese vector font generation using a Transformer architecture and specialized loss functions.
Findings
First Chinese vector font generated automatically with minimal references
Transformer architecture effectively captures structural features of Chinese characters
Method demonstrates potential for scalable Chinese font design
Abstract
Designing fonts for Chinese characters is highly labor-intensive and time-consuming. While the latest methods successfully generate the English alphabet vector font, despite the high demand for automatic font generation, Chinese vector font generation has been an unsolved problem owing to its complex shape and numerous characters. This study addressed the problem of automatically generating Chinese vector fonts from only a single style and content reference. We proposed a novel network architecture with Transformer and loss functions to capture structural features without differentiable rendering. Although the dataset range was still limited to the sans-serif family, we successfully generated the Chinese vector font for the first time using the proposed method.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsHandwritten Text Recognition Techniques · Human Motion and Animation · Video Analysis and Summarization
MethodsAttention Is All You Need · Linear Layer · Softmax · Dropout · Dense Connections · Position-Wise Feed-Forward Layer · Absolute Position Encodings · Multi-Head Attention · Byte Pair Encoding · Label Smoothing
