Automatic Method Illustration Generation for AI Scientific Papers via Drawing Middleware Creation, Evolution, and Orchestration
Zhuoling Li, Jiarui Zhang, Ping Hu, Jason Kuen, Jiuxiang Gu, Hossein Rahmani, Jun Liu

TL;DR
This paper introduces FigAgent, a multi-agent framework that automates the creation of scientific method illustrations by mimicking human drawing practices, using reusable middlewares and an explore-and-select strategy.
Contribution
The paper presents a novel multi-agent system with reusable drawing middlewares and an explore-and-select strategy for automatic, high-quality method illustration generation.
Findings
Effective in generating complex scientific illustrations
Outperforms baseline methods in quality and adaptability
Demonstrates robustness across diverse MI styles
Abstract
Method illustrations (MIs) play a crucial role in conveying the core ideas of scientific papers, yet their generation remains a labor-intensive process. Here, we take inspiration from human authors' drawing practices and correspondingly propose \textbf{FigAgent}, a novel multi-agent framework for high-quality automatic MI generation. Our FigAgent distills drawing experiences from similar components across MIs and encapsulates them into reusable drawing middlewares that can be orchestrated for MI generation, while evolving these middlewares to adapt to dynamically evolving drawing requirements. Besides, a novel Explore-and-Select drawing strategy is introduced to mimic the human-like trial-and-error manner for gradually constructing MIs with complex structures. Extensive experiments show the efficacy of our method.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
