Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

AutoFigure-Edit: Generating Editable Scientific Illustration

Zhen Lin, Qiujie Xie, Minjun Zhu, Shichen Li, Qiyao Sun, Enhao Gu, Yiran Ding, Ke Sun, Fang Guo, Panzhong Lu, Zhiyuan Ning, Yixuan Weng, Yue Zhang

TL;DR

AutoFigure-Edit is presented, an end-to-end system that generates fully editable scientific illustrations from long-form scientific text while enabling flexible style adaptation through user-provided reference images by combining long-context understanding, reference-guided styling, and native SVG editing.

Abstract

High-quality scientific illustrations are essential for communicating complex scientific and technical concepts, yet existing automated systems remain limited in editability, stylistic controllability, and efficiency. We present AutoFigure-Edit, an end-to-end system that generates fully editable scientific illustrations from long-form scientific text while enabling flexible style adaptation through user-provided reference images. By combining long-context understanding, reference-guided styling, and native SVG editing, it enables efficient creation and refinement of high-quality scientific illustrations. To facilitate further progress in this field, we release the video at https://youtu.be/10IH8SyJjAQ, full codebase at https://github.com/ResearAI/AutoFigure-Edit and provide a website for easy access and interactive use at https://deepscientist.cc/.

AutoFigure-Edit: Generating Editable Scientific Illustration

TL;DR

AutoFigure-Edit is presented, an end-to-end system that generates fully editable scientific illustrations from long-form scientific text while enabling flexible style adaptation through user-provided reference images by combining long-context understanding, reference-guided styling, and native SVG editing.

Abstract

High-quality scientific illustrations are essential for communicating complex scientific and technical concepts, yet existing automated systems remain limited in editability, stylistic controllability, and efficiency. We present AutoFigure-Edit, an end-to-end system that generates fully editable scientific illustrations from long-form scientific text while enabling flexible style adaptation through user-provided reference images. By combining long-context understanding, reference-guided styling, and native SVG editing, it enables efficient creation and refinement of high-quality scientific illustrations. To facilitate further progress in this field, we release the video at https://youtu.be/10IH8SyJjAQ, full codebase at https://github.com/ResearAI/AutoFigure-Edit and provide a website for easy access and interactive use at https://deepscientist.cc/.
Paper Structure (18 sections, 1 equation, 6 figures, 2 tables)

This paper contains 18 sections, 1 equation, 6 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. AutoFigure-Edit
  4. Framework Overview
  5. Stage I: Style-Conditioned Image Synthesis
  6. Stage II: Segmentation and Structural Indexing
  7. Stage III: Asset Extraction
  8. Stage IV: SVG Template Generation and Refinement
  9. Stage V: Asset Injection
  10. Applications
  11. Evaluation
  12. Quantitative Analysis
  13. Experimental Setup.
  14. User Study
  15. Conclusion
  16. ...and 3 more sections

Figures (6)

  • Figure 1: An overview of AutoFigure-Edit. This figure is also produced by AutoFigure-Edit and serves as a qualitative showcase of its generation quality.
  • Figure 2: Representative outputs of AutoFigure-Edit. (a)-(b) are bitmap (PNG) figures generated from long-form scientific descriptions across various domains. (c) shows the PNG-to-SVG conversion case of AutoFigure-Edit, including the original bitmap (bottom) and its corresponding vectorized SVG result (down). (d) is the web interface of AutoFigure-Edit, allowing users to select predefined style templates or upload custom reference images.
  • Figure 3: The embedded interactive canvas enables users to freely manipulate individual components within the generated SVG.
  • Figure 4: Results of the human user study. The numbers indicate the mean scores. AutoFigure-Edit achieves consistently high satisfaction in most metrics.
  • Figure 5: Qualitative results of AutoFigure-Edit.
  • ...and 1 more figures