用自然语言生成可编辑的矢量图，让设计更高效
SVGen: Interpretable Vector Graphics Generation with Large Language Models
- 基于百万级图文对数据训练，实现从文本到SVG的端到端生成
- 在语义准确性和结构完整性上超越通用大模型和传统方法
- 适合设计师和开发者快速生成可编辑的矢量图形
可缩放矢量图形（SVG）因其可缩放性、可编辑性和渲染效率，广泛应用于前端开发与UI/UX设计。然而，将创意想法转化为精确的矢量图形仍耗时费力。为此，我们构建了SVG-1M，一个大规模高质量的带自然语言描述的SVG数据集。通过先进的数据增强与标注，创建了对齐良好的“文本到SVG”训练样本，并包含带有思维链（Chain of Thought）注释的子集以增强语义引导。基于此数据集，我们提出SVGen，一种从自然语言输入生成SVG代码的端到端模型。该方法通过课程学习与强化学习优化，确保生成结果具备语义准确性与结构完整性。实验表明，SVGen在有效性与效率方面均优于通用大模型及传统渲染方法。代码、模型与数据集已开源。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。