Infographic charts are a powerful medium for communicating abstract data by combining visual elements (e.g., charts, images) with textual information. However, their visual and structural richness poses challenges for large vision-language models (LVLMs), which are typically trained on plain charts. To bridge this gap, we introduce ChartGalaxy, a million-scale dataset designed to advance the understanding and generation of infographic charts. The dataset is constructed through an inductive process that identifies 75 chart types, 440 chart variations, and 68 layout templates from real infographic charts and uses them to create synthetic ones programmatically. We showcase the utility of this dataset through: 1) improving infographic chart understanding via fine-tuning, 2) benchmarking code generation for infographic charts, and 3) enabling example-based infographic chart generation. By capturing the visual and structural complexity of real design, ChartGalaxy provides a useful resource for enhancing multimodal reasoning and generation in LVLMs.
@article{arxiv.2505.18668,
title = {ChartGalaxy: A Dataset for Infographic Chart Understanding and Generation},
author = {Zhen Li and Duan Li and Yukai Guo and Xinyuan Guo and Bowen Li and Lanxi Xiao and Shenyu Qiao and Jiashu Chen and Zijian Wu and Hui Zhang and Xinhuan Shu and Shixia Liu},
journal= {arXiv preprint arXiv:2505.18668},
year = {2025}
}