ChartReformer:自然语言驱动的图表图像编辑
ChartReformer: Natural Language-Driven Chart Image Editing
AI总结:
本文提出ChartReformer,通过自然语言指令直接编辑图表图像,无需原始数据,模型可推理生成底层数据表与视觉属性,并标准化多种编辑类型,实验验证了其有效性。
摘要:
图表可视化对于数据解读与交流至关重要;然而,大多数图表仅以图像格式存在,缺乏相应的数据表和补充信息,使得在不同应用场景下难以改变其外观。为了在无需原始底层数据和信息的情况下执行图表编辑,我们提出了ChartReformer,这是一种自然语言驱动的图表图像编辑解决方案,可直接根据输入的图像和给定的指令提示对图表进行编辑。该方法的关键在于,我们让模型理解图表并对提示进行推理,从而生成新图表对应的底层数据表和视觉属性,实现精确编辑。此外,为了使ChartReformer具有泛化能力,我们定义并标准化了多种类型的图表编辑,涵盖样式、布局、格式以及以数据为中心的编辑。实验表明,自然语言驱动的图表图像编辑取得了有前景的结果。
英文摘要:
Chart visualizations are essential for data interpretation and communication; however, most charts are only accessible in image format and lack the corresponding data tables and supplementary information, making it difficult to alter their appearance for different application scenarios. To eliminate the need for original underlying data and information to perform chart editing, we propose ChartReformer, a natural language-driven chart image editing solution that directly edits the charts from the input images with the given instruction prompts. The key in this method is that we allow the model to comprehend the chart and reason over the prompt to generate the corresponding underlying data table and visual attributes for new charts, enabling precise edits. Additionally, to generalize ChartReformer, we define and standardize various types of chart editing, covering style, layout, format, and data-centric edits. The experiments show promising results for the natural language-driven chart image editing.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。