FigGen: Text to Scientific Figure Generation
This work addresses a domain-specific need for researchers and authors by extending generative modeling to scientific figures, which is an incremental step beyond natural image generation.
The paper tackles the problem of generating scientific figures from text descriptions, introducing FigGen, a diffusion-based approach, and addressing the main challenges of this task.
The generative modeling landscape has experienced tremendous growth in recent years, particularly in generating natural images and art. Recent techniques have shown impressive potential in creating complex visual compositions while delivering impressive realism and quality. However, state-of-the-art methods have been focusing on the narrow domain of natural images, while other distributions remain unexplored. In this paper, we introduce the problem of text-to-figure generation, that is creating scientific figures of papers from text descriptions. We present FigGen, a diffusion-based approach for text-to-figure as well as the main challenges of the proposed task. Code and models are available at https://github.com/joanrod/figure-diffusion