cs.CVMar 3, 2026

AutoFigure-Edit: Generating Editable Scientific Illustration

Authors: Zhen Lin, Qiujie Xie, Minjun Zhu, Shichen Li, Qiyao Sun, Enhao Gu, Yiran Ding, Ke Sun, 

Organizations: Engineering School, Westlake University · Zhejiang University · Soochow University

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

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/.

Figures & tables

MethodSci. Gen.EditableStyle ControlGUI Support
StarVector & OmniSVG ( Rodriguez et al., 2025 ; Yang et al., 2025 )Limited✓Prompt (Hard)Web Only
AutomaTikZ ( Belouadi et al., 2024a )✓✓Prompt (Hard)Web Only
DeTikZify ( Belouadi et al., 2024b )✓✓Sketch (Hard)Web Only
GPT-Image ( Hurst et al., 2024 )✓✗Prompt (Hard)Web Only
Diagram Agent ( Wei et al., 2025 )✓✓Prompt (Hard)None
PaperBanana ( Zhu et al., 2026a )✓✗Prompt (Hard)Web Only
Table 1: Comparison of AutoFigure-Edit with other relevant systems. “Sci. Gen.” denotes scientific illustration generation; “GUI Support” denotes the level of integrated graphical user interface and editing capabilities.
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.
Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

Figure 5: Qualitative results of AutoFigure-Edit .
Figure 6: Comparison between Reference Images and Generated Images.
More in this topic

Scientific Visualization

Scientific visualization turns complex scientific data into visual representations for analysis, exploration, and communication.

See all 53 papers

Explore similar work

CardsList

  1. Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs

    May 28, 2026Haozhe Zhao, Shuzheng Si, Zhenhailong Wang +6Scientific Communication

    University of Illinois at Urbana-Champaign · Tsinghua University · Peking University

  2. SciFig: Towards Automating Editable Figure Generation for Scientific Papers

    Jan 7, 2026Siyuan Huang, Yifan Zhou, Yutong Gao +8

    Johns Hopkins University · Zhejiang University · Independant Researcher +4

  3. EdiTikZ: Scientific Figure Editing from Revision Trajectories

    Sep 1, 2026Christian Greisinger, Zhixue Zhao, Steffen EgerVision-Language Models

    University of Technology Nuremberg · University of Sheffield