气味绘画：通过大语言模型和生成式人工智能探索气味可视化
Paint by Odor: An Exploration of Odor Visualization through Large Language Model and Generative AI
AI总结：
本文提出通过大语言模型和生成式人工智能实现自动气味可视化的方法，探索了气味感知与生成工具的结合，揭示了语言描述和抽象风格对气味图像生成的影响。
摘要：
气味可视化将气味信息和感知转化为视觉结果，并引发相应的嗅觉通感，超越了气味只能在存在处被感知的空间限制。传统的气味可视化通常依赖于一维映射，如气味-颜色关联，并需要大量的手动设计工作。然而，生成式人工智能（Gen AI）和大语言模型（LLMs）的出现为自动气味可视化提供了新的机会。然而，仍存在将嗅觉感知与生成工具结合以生成气味图像的差距。为了解决这些差距，本文介绍了Paint by Odor，一个利用Gen AI和LLMs将嗅觉感知转化为丰富、具有审美吸引力的视觉表示的流程。进行了两个实验，其中30名参与者闻了现实中的气味并提供了描述数据，28名参与者通过七个系统设计的提示评估了560个生成的气味图像。我们的发现探索了LLMs在生成嗅觉感知方面的能力，并将其与人类反应进行比较，揭示了基于语言的描述和几种抽象风格对气味可视化的影响机制和效果。我们的工作进一步讨论了无需人类参与的自动气味可视化可能性。这些探索和结果填补了使用LLMs和Gen AI进行气味可视化研究的空白，提供了有价值的设计见解和未来应用的各种可能性。
英文摘要：
Odor visualization translates odor information and perception into visual outcomes and arouses the corresponding olfactory synesthesia, surpassing the spatial limitation that odors can only be perceived where they are present. Traditional odor visualization has typically relied on unidimensional mappings, such as odor-to-color associations, and has required extensive manual design efforts. However, the advent of generative AI (Gen AI) and large language models (LLMs) presents a new opportunity for automatic odor visualization. Nonetheless, gaps remain in bridging olfactory perception with generative tools to produce odor images. To address these gaps, this paper introduces Paint by Odor, a pipeline that leverages Gen AI and LLMs to transform olfactory perceptions into rich, aesthetically engaging visual representations. Two experiments were conducted, where 30 participants smelled real-world odors and provided descriptive data and 28 participants evaluated 560 generated odor images through seven systematically designed prompts. Our findings explored the capability of LLMs in producing olfactory perception by comparing it with human responses and revealed the underlying mechanisms and effects of language-based descriptions and several abstraction styles on odor visualization. Our work further discussed the possibility of automatic odor visualization without human participation. These explorations and results have bridged the research gap in odor visualization using LLMs and Gen AI, offering valuable design insights and various possibilities for future applications.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
