Stroke Modeling Enables Vectorized Character Generation with Large Vectorized Glyph Model

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhang, Xinyue, Li, Haolong, Ma, Jiawei, Ye, Chen
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915618143338496
author Zhang, Xinyue
Li, Haolong
Ma, Jiawei
Ye, Chen
author_facet Zhang, Xinyue
Li, Haolong
Ma, Jiawei
Ye, Chen
contents Vectorized glyphs are widely used in poster design, network animation, art display, and various other fields due to their scalability and flexibility. In typography, they are often seen as special sequences composed of ordered strokes. This concept extends to the token sequence prediction abilities of large language models (LLMs), enabling vectorized character generation through stroke modeling. In this paper, we propose a novel Large Vectorized Glyph Model (LVGM) designed to generate vectorized Chinese glyphs by predicting the next stroke. Initially, we encode strokes into discrete latent variables called stroke embeddings. Subsequently, we train our LVGM via fine-tuning DeepSeek LLM by predicting the next stroke embedding. With limited strokes given, it can generate complete characters, semantically elegant words, and even unseen verses in vectorized form. Moreover, we release a new large-scale Chinese SVG dataset containing 907,267 samples based on strokes for dynamically vectorized glyph generation. Experimental results show that our model has scaling behaviors on data scales. Our generated vectorized glyphs have been validated by experts and relevant individuals.
format Preprint
id arxiv_https___arxiv_org_abs_2511_11119
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Stroke Modeling Enables Vectorized Character Generation with Large Vectorized Glyph Model
Zhang, Xinyue
Li, Haolong
Ma, Jiawei
Ye, Chen
Computer Vision and Pattern Recognition
Vectorized glyphs are widely used in poster design, network animation, art display, and various other fields due to their scalability and flexibility. In typography, they are often seen as special sequences composed of ordered strokes. This concept extends to the token sequence prediction abilities of large language models (LLMs), enabling vectorized character generation through stroke modeling. In this paper, we propose a novel Large Vectorized Glyph Model (LVGM) designed to generate vectorized Chinese glyphs by predicting the next stroke. Initially, we encode strokes into discrete latent variables called stroke embeddings. Subsequently, we train our LVGM via fine-tuning DeepSeek LLM by predicting the next stroke embedding. With limited strokes given, it can generate complete characters, semantically elegant words, and even unseen verses in vectorized form. Moreover, we release a new large-scale Chinese SVG dataset containing 907,267 samples based on strokes for dynamically vectorized glyph generation. Experimental results show that our model has scaling behaviors on data scales. Our generated vectorized glyphs have been validated by experts and relevant individuals.
title Stroke Modeling Enables Vectorized Character Generation with Large Vectorized Glyph Model
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.11119