FigMirror：定位它、编码它、绘制它
FigMirror: Ground It, Code It, Plot It
查看机构详情
- MBZUAI（穆罕默德·本·扎耶德人工智能大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
本文提出FigMirror智能体框架，通过定位测量结合PlotTwin-Bench基准，实现科学图表风格迁移至新数据，性能优于现有方法，论文图表多由其生成。
中文摘要 AI 辅助
将科学图表转换为可执行代码已受到越来越多的关注，但现有方法主要聚焦于复现参考图表本身。更实用的场景是在绘制新数据的同时保留参考图表的视觉风格（如配色方案和排版）。现有方法通过像素级优化模仿参考图表，难以将其风格迁移到新数据。我们表明，该任务的关键在于现代计算机使用模型具备的坐标定位与编码能力。我们提出FigMirror，这是一个智能体框架，通过「定位测量（Grounded Measurement）」解锁这些能力，该方法通过坐标定位视觉元素并通过可执行代码测量其属性。我们还引入了PlotTwin-Bench，这是一个由专家精心构建的基准，具备细粒度的代码级和图像级风格指标。实验表明，FigMirror在参考条件下的风格迁移任务中始终优于现有方法。本文所有图表均由FigMirror生成，除了那些为对比而由其他方法生成的图表。我们的代码和数据可在此URL获取。
英文摘要
Converting scientific figures into executable code has gained increasing attention, yet existing methods primarily focus on reproducing the reference figure itself. A more practical setting is to plot new data while preserving the visual style of a reference figure (e.g., color scheme and typography). Prior approaches mimic the reference through pixel-level optimization and struggle to carry its style to new data. We show that the key to this task lies in the coordinate grounding and coding capabilities present in modern computer-use models. We propose FigMirror, an agentic framework that unlocks these capabilities through Grounded Measurement, which locates visual elements by coordinates and measures their properties through executable code. We further introduce PlotTwin-Bench, an expert-curated benchmark with fine-grained code and image-level style metrics. Experiments show that FigMirror consistently outperforms existing methods on reference-conditioned style transfer. All plots in this paper are generated by FigMirror, except those produced by other methods for comparison. Our code and data are available at: https://github.com/VILA-Lab/FigMirror.
