Technology Category
Natural Language Processing: Code Generation / Program Synthesis from Natural LanguageComputer Vision: Computational Photography, Image & Video SynthesisCognitive Modeling & Cognitive Systems: Computational Creativity
AutoFigure-Edit: Generating Editable Scientific Illustration
🤖 AI Summary
Existing methods for scientific illustration generation suffer from limitations in editability, style controllability, and computational efficiency. This work proposes the first end-to-end system capable of directly generating fully editable SVG illustrations from long-form scientific texts, while supporting reference-image-guided style transfer. By integrating long-context language understanding, image-driven style control, and native SVG synthesis, the approach enables high-quality, efficient, and interactively friendly illustration creation. The contributions include publicly released source code, an online demo platform, and accompanying tutorial videos, collectively enhancing the flexibility and productivity of scientific visualization workflows.
Technology Category
Application Category
📝 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/.
Problem
Research questions and friction points this paper is trying to address.
scientific illustration
editability
stylistic controllability
automated generation
Innovation
Methods, ideas, or system contributions that make the work stand out.
editable scientific illustration
reference-guided styling
long-context understanding
SVG editing
end-to-end generation
🔎 Similar Papers
No similar papers found.
