让论文图表自动套用风格并生成新数据图，像编程一样精准
FigMirror: Ground It, Code It, Plot It
- 通过坐标定位和可执行代码测量，精准捕捉图表元素
- 在新数据上复现参考图风格，准确率显著优于现有方法
- 适合需要快速生成合规科研图的学者与工程师
将科学图表转换为可执行代码受到越来越多关注，但现有方法多聚焦于复现参考图表本身。更实用的场景是：在保持参考图表视觉风格（如配色、字体）的前提下，绘制新数据。以往方法依赖像素级优化，难以将风格迁移到新数据。我们发现关键在于现代计算机使用模型的坐标定位与编码能力。为此提出FigMirror——一种代理式框架，通过‘坐标锚定’机制，以坐标定位视觉元素，并用可执行代码测量其属性。进一步构建了专家精调的PlotTwin-Bench基准，包含细粒度代码与图像级风格指标。实验表明，FigMirror在参考条件下的风格迁移任务中持续优于现有方法。本文所有图表均由FigMirror生成，仅对比图表来自其他方法。代码与数据已公开：https://github.com/VILA-Lab/FigMirror。
原文摘要 · Abstract (English)
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.
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。