arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.01063cs.HCcs.GR
收藏

Chat Modeling:无需训练、基于自然语言的生物结构程序化建模

Chat Modeling: Natural Language-based Procedural Modeling of Biological Structures without Training

Donggang Jia, Yunhai Wang, Ivan Viola

AI总结:

本文提出Chat Modeling框架,利用大型语言模型将用户文本输入转换为程序化建模操作,并通过用户细化机制交互改进三维生物结构建模,无需传统训练,为结构生物学家提供了自动和逐步建模工具。

摘要:

生物结构的三维建模本质上是一个复杂过程,既需要生物学理解,也需要几何理解。此外,三维建模工具用户界面的复杂性以及随之而来的陡峭学习曲线,进一步加剧了创建三维模型的难度。在本文中,我们引入了一个新颖框架,通过将用户的文本输入转换为交互式程序化建模系统中的建模操作,来应对使用三维建模软件的挑战。该框架包含一种新颖代码格式的代码生成器以及相应的代码解释器。主要技术创新包括用户细化机制,该机制捕获用户对建模结果的不满意程度,提供交互式修订,并利用这些反馈改进未来的三维建模。整个框架由大型语言模型驱动,并消除了对传统训练过程的需求。我们开发了一个名为Chat Modeling的原型工具,提供自动和逐步两种三维建模方法。我们与结构生物学家一起对该框架进行的评估表明,我们的方法有潜力被用于他们的科学工作流程中。所有补充材料可在https://osf.io/x4qb7/获取。

英文摘要:

3D modeling of biological structures is an inherently complex process, necessitating both biological and geometric understanding. Additionally, the complexity of user interfaces of 3D modeling tools and the associated steep learning curve further exacerbate the difficulty of authoring a 3D model. In this paper, we introduce a novel framework to address the challenge of using 3D modeling software by converting users' textual inputs into modeling actions within an interactive procedural modeling system. The framework incorporates a code generator of a novel code format and a corresponding code interpreter. The major technical innovation includes the user-refinement mechanism that captures the degree of user dissatisfaction with the modeling outcome, offers an interactive revision, and leverages this feedback for future improved 3D modeling. This entire framework is powered by large language models and eliminates the need for a traditional training process. We develop a prototype tool named Chat Modeling, offering both automatic and step-by-step 3D modeling approaches. Our evaluation of the framework with structural biologists highlights the potential of our approach being utilized in their scientific workflows. All supplemental materials are available at https://osf.io/x4qb7/.

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。

↑