将图片版信息图转为可编辑的Google幻灯片，自动识别内容并重建布局。
From Dead Pixels to Editable Slides: Infographic Reconstruction into Native Google Slides via Vision-Language Region Understanding
- 用视觉语言模型分析图像区域，提取文本、图标等元素位置与内容。
- 文本恢复率98.5%，图像完全还原，布局匹配度达64.4%。
- 支持多模型后端，适合需要快速更新信息图的团队使用。
信息图常用于图文结合传递信息，但导出为图片后内容被锁定，难以修改、本地化或复用。本文提出 extsc{Images2Slides}，一个基于API的转换管道，通过视觉语言模型（VLM）提取区域级描述，将像素坐标映射为幻灯片坐标，并利用Google Slides批量更新接口重建可编辑幻灯片。系统具备模型无关性，通过统一的JSON区域格式和确定性后处理支持多种VLM后端。在29个程序生成的信息图基准测试中，整体元素恢复率达0.989±0.057（文本：0.985±0.083，图像：1.000±0.000），文本转录错误率（CER）为0.033±0.149，文本区域布局保真度（IoU）为0.364±0.161，图像区域为0.644±0.131。同时指出实际工程挑战，如字号校准与非均匀背景问题，并总结失败模式以指导未来研究。
原文摘要 · Abstract (English)
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.
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。