Search papers, labs, and topics across Lattice.
Chart2SVG is a multimodal large language model designed to convert static raster charts into semantically enriched and editable SVGs, enhancing programmatic editing capabilities. The model employs chart-specific semantic tokens and introduces Beagle+, a dataset of 33K structured chart samples, to ensure robust structural recovery. Experimental results demonstrate that Chart2SVG significantly outperforms existing methods in both reconstruction fidelity and utility for downstream editing tasks, marking a significant advancement in interactive visualization tools.
Transforming static charts into editable SVGs, Chart2SVG unlocks new possibilities for interactive data visualization and manipulation.
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.
