FigMirror: Ground It, Code It, Plot It

2026-08-28

AI Summary

本文提出FigMirror框架，通过坐标定位和代码测量解决科学图表风格迁移问题，使新数据保持参考图的视觉风格。

Abstract

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.

Problem

• scientific figures
• executable code
• visual style
• new data
• style transfer

Innovation

• coordinate grounding
• executable code
• visual style preservation
• PlotTwin-Bench