SVGen: Interpretable Vector Graphics Generation with Large Language Models

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Feiyu, Zhao, Zhiyuan, Liu, Yuandong, Zhang, Da, Gao, Junyu, Sun, Hao, Li, Xuelong
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913987612901376
author Wang, Feiyu
Zhao, Zhiyuan
Liu, Yuandong
Zhang, Da
Gao, Junyu
Sun, Hao
Li, Xuelong
author_facet Wang, Feiyu
Zhao, Zhiyuan
Liu, Yuandong
Zhang, Da
Gao, Junyu
Sun, Hao
Li, Xuelong
contents Scalable Vector Graphics (SVG) is widely used in front-end development and UI/UX design due to its scalability, editability, and rendering efficiency. However, turning creative ideas into precise vector graphics remains a time-consuming challenge. To address this, we introduce SVG-1M, a large-scale dataset of high-quality SVGs paired with natural language descriptions. Through advanced data augmentation and annotation, we create well-aligned Text to SVG training pairs, including a subset with Chain of Thought annotations for enhanced semantic guidance. Based on this dataset, we propose SVGen, an end-to-end model that generates SVG code from natural language inputs. Our approach ensures semantic accuracy and structural completeness, supported by curriculum learning and reinforcement learning optimization. Experiments show that SVGen outperforms general large models and traditional rendering methods in both effectiveness and efficiency. Code, model, and dataset are available on GitHub.
format Preprint
id arxiv_https___arxiv_org_abs_2508_09168
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SVGen: Interpretable Vector Graphics Generation with Large Language Models
Wang, Feiyu
Zhao, Zhiyuan
Liu, Yuandong
Zhang, Da
Gao, Junyu
Sun, Hao
Li, Xuelong
Machine Learning
Computer Vision and Pattern Recognition
Scalable Vector Graphics (SVG) is widely used in front-end development and UI/UX design due to its scalability, editability, and rendering efficiency. However, turning creative ideas into precise vector graphics remains a time-consuming challenge. To address this, we introduce SVG-1M, a large-scale dataset of high-quality SVGs paired with natural language descriptions. Through advanced data augmentation and annotation, we create well-aligned Text to SVG training pairs, including a subset with Chain of Thought annotations for enhanced semantic guidance. Based on this dataset, we propose SVGen, an end-to-end model that generates SVG code from natural language inputs. Our approach ensures semantic accuracy and structural completeness, supported by curriculum learning and reinforcement learning optimization. Experiments show that SVGen outperforms general large models and traditional rendering methods in both effectiveness and efficiency. Code, model, and dataset are available on GitHub.
title SVGen: Interpretable Vector Graphics Generation with Large Language Models
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.09168