将静态图表转为可编程编辑的SVG，支持结构化修改与可视化重用。
Chart2SVG: Editable SVG Generation from Raster Chart Images
- 通过视觉语言模型+专用语义标记，理解图表元素及其功能角色。
- 在33K个标准化图表上训练，生成视觉准确且结构一致的SVG。
- 构建图表结构图，支持交互探索与布局复用，适合数据可视化开发者。
我们提出Chart2SVG，一个将静态位图图表转换为结构化、语义丰富的可编程SVG的多模态大模型。通过在视觉-语言模型中引入图表特有语义标记，该模型能同时捕捉几何元素及其功能角色。为支持鲁棒的结构恢复，我们构建了包含33,000个规范化与结构提炼图表样本的Beagle+数据集。方法结合专项训练目标与渲染感知的后训练阶段，生成既视觉准确又结构一致的SVG。为进一步支持高层操作，我们构建了图表结构图（CSG），揭示视觉依赖关系，实现交互式探索、图表再利用和版面复用。实验表明，Chart2SVG在重建保真度与下游编辑实用性方面显著优于基线，推动智能交互可视化工具的发展。
原文摘要 · Abstract (English)
We present Chart2SVG, a multimodal large language model that converts static raster charts into structurally organized, semantically enriched SVGs that support programmatic editing. By incorporating chart-specific semantic tokens into a vision-language model, Chart2SVG captures both geometric primitives and their functional roles. To support robust structural recovery, we introduce Beagle+, a dataset of 33K canonicalized and structurally distilled chart samples. Our approach combines specialized training objectives with a rendering-aware post-training phase, producing SVGs that are both visually accurate and structurally consistent. To facilitate higher-level manipulations, we construct a Chart Structure Graph (CSG) that exposes visual dependencies, enabling tasks such as interactive exploration, chart repurposing, and layout reuse. Experiments show that Chart2SVG substantially outperforms baselines in reconstruction fidelity and downstream editing utility, advancing the development of intelligent and interactive visualization tools.
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。