用融合代码与图像的生成模型，让文本变可编辑的高质量矢量图
SVGFusion: A VAE-Diffusion Transformer for Vector Graphic Generation
- 用代码和图像联合编码学习视觉丰富的潜在空间
- 通过迭代优化生成结构一致、语义对齐的矢量图
- 适合需要可编辑矢量图的AI设计场景
从文本生成高质量可缩放矢量图形（SVG）仍面临挑战。现有基于大语言模型的方法将SVG代码作为扁平标记序列生成，存在结构理解差和错误累积问题；而基于优化的方法速度慢且输出不可编辑。为此，我们提出SVGFusion，一种统一框架，将变分自编码器-扩散架构适配于兼具代码与视觉特性的SVG。模型包含两个核心组件：向量-像素融合变分自编码器（VP-VAE），通过联合编码SVG代码及其渲染图像，学习感知丰富的潜在空间；以及向量空间扩散变换器（VS-DiT），通过迭代精炼实现全局结构一致的构图。此外，引入渲染顺序建模策略，确保对象层级与遮挡关系准确。在包含24万张人工设计SVG的SVGX-Dataset上评估，SVGFusion达到新基准，生成高质量、可编辑且严格语义对齐输入文本的SVG。
原文摘要 · Abstract (English)
Generating high-quality Scalable Vector Graphics (SVGs) from text remains a significant challenge. Existing LLM-based models that generate SVG code as a flat token sequence struggle with poor structural understanding and error accumulation, while optimization-based methods are slow and yield uneditable outputs. To address these limitations, we introduce SVGFusion, a unified framework that adapts the VAE-diffusion architecture to bridge the dual code-visual nature of SVGs. Our model features two core components: a Vector-Pixel Fusion Variational Autoencoder (VP-VAE) that learns a perceptually rich latent space by jointly encoding SVG code and its rendered image, and a Vector Space Diffusion Transformer (VS-DiT) that achieves globally coherent compositions through iterative refinement. Furthermore, this architecture is enhanced by a Rendering Sequence Modeling strategy, which ensures accurate object layering and occlusion. Evaluated on our novel SVGX-Dataset comprising 240k human-designed SVGs, SVGFusion establishes a new state-of-the-art, generating high-quality, editable SVGs that are strictly semantically aligned with the input text.
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。