AutoFigure: Generating and Refining Publication-Ready Scientific Illustrations
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911442971656192 |
|---|---|
| author | Zhu, Minjun Lin, Zhen Weng, Yixuan Lu, Panzhong Xie, Qiujie Wei, Yifan Liu, Sifan Sun, Qiyao Zhang, Yue |
| author_facet | Zhu, Minjun Lin, Zhen Weng, Yixuan Lu, Panzhong Xie, Qiujie Wei, Yifan Liu, Sifan Sun, Qiyao Zhang, Yue |
| contents | 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 present FigureBench, the first large-scale benchmark for generating scientific illustrations from long-form scientific texts. It contains 3,300 high-quality scientific text-figure pairs, covering diverse text-to-illustration tasks from scientific papers, surveys, blogs, and textbooks. Moreover, we propose AutoFigure, the first agentic framework that automatically generates high-quality scientific illustrations based on long-form scientific text. Specifically, before rendering the final result, AutoFigure engages in extensive thinking, recombination, and validation to produce a layout that is both structurally sound and aesthetically refined, outputting a scientific illustration that achieves both structural completeness and aesthetic appeal. Leveraging the high-quality data from FigureBench, we conduct extensive experiments to test the performance of AutoFigure against various baseline methods. The results demonstrate that AutoFigure consistently surpasses all baseline methods, producing publication-ready scientific illustrations. The code, dataset and huggingface space are released in https://github.com/ResearAI/AutoFigure. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_03828 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | AutoFigure: Generating and Refining Publication-Ready Scientific Illustrations Zhu, Minjun Lin, Zhen Weng, Yixuan Lu, Panzhong Xie, Qiujie Wei, Yifan Liu, Sifan Sun, Qiyao Zhang, Yue Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition Digital Libraries 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 present FigureBench, the first large-scale benchmark for generating scientific illustrations from long-form scientific texts. It contains 3,300 high-quality scientific text-figure pairs, covering diverse text-to-illustration tasks from scientific papers, surveys, blogs, and textbooks. Moreover, we propose AutoFigure, the first agentic framework that automatically generates high-quality scientific illustrations based on long-form scientific text. Specifically, before rendering the final result, AutoFigure engages in extensive thinking, recombination, and validation to produce a layout that is both structurally sound and aesthetically refined, outputting a scientific illustration that achieves both structural completeness and aesthetic appeal. Leveraging the high-quality data from FigureBench, we conduct extensive experiments to test the performance of AutoFigure against various baseline methods. The results demonstrate that AutoFigure consistently surpasses all baseline methods, producing publication-ready scientific illustrations. The code, dataset and huggingface space are released in https://github.com/ResearAI/AutoFigure. |
| title | AutoFigure: Generating and Refining Publication-Ready Scientific Illustrations |
| topic | Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition Digital Libraries |
| url | https://arxiv.org/abs/2602.03828 |