Automatic Method Illustration Generation for AI Scientific Papers via Drawing Middleware Creation, Evolution, and Orchestration
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
AutoFigure: Generating and Refining Publication-Ready Scientific Illustrations
High-quality scientific illustrations are crucial for effectively communicating complex scientific and technical concepts, yet their manual creation remains a well-recognized bottleneck in both academia and industry. We …
SciDraw-6K: A Multilingual Scientific Illustration Dataset Generated by Google Gemini
We present SciDraw-6K, a curated dataset of 6,291 scientific illustrations synthesized by Google Gemini image-generation models, each paired with prompts in eleven languages (English, Simplified Chinese, Traditional Chin…
TechImage-Bench: Rubric-Based Evaluation for Technical Image Generation
We study technical image generation, where a model must synthesize information-dense, scientifically precise illustrations from detailed descriptions rather than merely produce visually plausible pictures. To quantify th…
Image GenerationAutoLLM-CARD: Towards a Description and Landscape of Large Language Models
With the rapid growth of the Natural Language Processing (NLP) field, a vast variety of Large Language Models (LLMs) continue to emerge for diverse NLP tasks. As more papers are published, researchers and developers face…
Knowledge Graphsnamed-entity-recognitionNamed Entity RecognitionNER+1SciPostLayout: A Dataset for Layout Analysis and Layout Generation of Scientific Posters
Scientific posters are used to present the contributions of scientific papers effectively in a graphical format. However, creating a well-designed poster that efficiently summarizes the core of a paper is both labor-inte…
Layout Generation