从死像素到可编辑幻灯片：通过视觉-语言区域理解将信息图转换为原生Google幻灯片
From Dead Pixels to Editable Slides: Infographic Reconstruction into Native Google Slides via Vision-Language Region Understanding
AI总结：
通过视觉-语言区域理解，将信息图转换为可编辑的Google幻灯片，实现元素恢复和布局保真度的高精度转换。
摘要：
信息图广泛用于通过文本、图标和数据可视化结合的方式传达信息，但一旦导出为图像，其内容就固定在像素中，使得更新、本地化和重用成本高昂。我们描述了\textsc{Images2Slides}，一个基于API的管道，它通过视觉-语言模型（VLM）提取区域级规范，将静态信息图（PNG/JPG）转换为原生、可编辑的Google幻灯片幻灯片。该系统是模型无关的，并通过通用的JSON区域模式和确定性的后处理支持多种VLM后端。在受控基准测试中，29个程序生成的信息图幻灯片（已知地面真实区域）上，\textsc{Images2Slides}实现了整体元素恢复率为$0.989\pm0.057$（文本：$0.985\pm0.083$，图像：$1.000\pm0.000$），平均文本转录错误率为$\mathrm{CER}=0.033\pm0.149$，平均布局保真度为$\mathrm{IoU}=0.364\pm0.161$（文本区域）和$0.644\pm0.131$（图像区域）。我们还突出了重建中的实际工程挑战，包括文本大小校准和非均匀背景，并描述了导致未来工作的失败模式。
英文摘要：
Infographics are widely used to communicate information with a combination of text, icons, and data visualizations, but once exported as images their content is locked into pixels, making updates, localization, and reuse expensive. We describe \textsc{Images2Slides}, an API-based pipeline that converts a static infographic (PNG/JPG) into a native, editable Google Slides slide by extracting a region-level specification with a vision-language model (VLM), mapping pixel geometry into slide coordinates, and recreating elements using the Google Slides batch update API. The system is model-agnostic and supports multiple VLM backends via a common JSON region schema and deterministic postprocessing. On a controlled benchmark of 29 programmatically generated infographic slides with known ground-truth regions, \textsc{Images2Slides} achieves an overall element recovery rate of $0.989\pm0.057$ (text: $0.985\pm0.083$, images: $1.000\pm0.000$), with mean text transcription error $\mathrm{CER}=0.033\pm0.149$ and mean layout fidelity $\mathrm{IoU}=0.364\pm0.161$ for text regions and $0.644\pm0.131$ for image regions. We also highlight practical engineering challenges in reconstruction, including text size calibration and non-uniform backgrounds, and describe failure modes that guide future work.
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。
