VecFontLLM: Anchor-Guided Direct Synthesis of Chinese Vector Fonts
Computer Vision and Pattern Recognition
Summary
The authors address the difficulty in creating Chinese vector fonts directly because these fonts have complicated parts and curves mixed together. They propose VecFontLLM, a system that first predicts key anchor points to outline the glyph structure, then fills in detailed curves, making the process easier and more accurate. Their method generates fonts directly as vectors without turning images into vectors afterward, improving reliability especially for complex characters. Tests show their approach outperforms previous vector font methods and produces results similar to image-based techniques.
Authors
Hao Yuan, Yuxuan Luo, Xing Chen, Zhouhui Lian
Abstract
Direct generation of Chinese vector fonts is a challenging and ongoing problem. A Chinese vector glyph contains complex component structure, anchor layout, and Bézier curve details, which work at different scales, but a standard vector sequence writes them together in one long sequence, making the task of vector font synthesis challenging. Existing direct vector generators often fail on complex characters, while raster-domain methods must vectorize the synthesized glyph images afterward. To address the above-mentioned problem, this paper proposes VecFontLLM, an anchor-guided multimodal large language model for direct few-shot synthesis of Chinese vector fonts. Our key idea is to generate vector glyphs through anchors rather than a standard vector sequence. Specifically, the proposed VecFontLLM first predicts and refines an anchor scaffold that fixes the coarse layout of components and contours, and then completes Bézier control points to recover local curvature and style. At test time, a confidence-guided generation chain samples multiple component candidates and continues synthesis from the highest-confidence one, improving stability for complex glyphs. This work demonstrates, for the first time, high-quality few-shot synthesis of complex Chinese vector glyphs directly in the vector domain, without raster generation or vectorization. Experiments on several Chinese font datasets show substantial improvements over existing vector font synthesis methods, competitive glyph rendering quality against raster-domain baselines, and vector command distributions close to real fonts.