arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2405.08037cs.HCcs.AI
收藏

基于大语言模型的布局生成智能体

Layout Generation Agents with Large Language Models

Hitachi, Ltd.(日立公司)

Yuichi Sasazawa, Yasuhiro Sogawa

AI总结:

针对3D虚拟空间布局生成效率低、现有方法未利用生成过程信息的问题,提出基于GPT-4V的智能体驱动布局生成系统,可高成功率生成符合指令的虚拟空间,并通过消融实验明确了性能提升的关键要素。

摘要:

近年来,可定制3D虚拟空间的需求持续增长。由于创建这类虚拟空间需耗费大量人力,提升虚拟空间的创建效率成为亟待解决的问题。现有研究虽已提出平面图、家具排布等布局自动生成方法,但这类方法仅能根据用户指令生成表征布局结构的文本,并未利用生成过程中获取的信息。本研究提出一种基于GPT-4V多模态大语言模型的智能体驱动布局生成系统,并验证了其有效性。具体而言,该语言模型操控智能体在虚拟空间中依次放置物体,从而生成符合用户指令的布局。实验结果证实,本文提出的方法能够以高成功率生成符合用户指令的虚拟空间。此外,本研究通过消融实验成功识别出有助于提升行为生成性能的要素。

英文摘要:

In recent years, there has been an increasing demand for customizable 3D virtual spaces. Due to the significant human effort required to create these virtual spaces, there is a need for efficiency in virtual space creation. While existing studies have proposed methods for automatically generating layouts such as floor plans and furniture arrangements, these methods only generate text indicating the layout structure based on user instructions, without utilizing the information obtained during the generation process. In this study, we propose an agent-driven layout generation system using the GPT-4V multimodal large language model and validate its effectiveness. Specifically, the language model manipulates agents to sequentially place objects in the virtual space, thus generating layouts that reflect user instructions. Experimental results confirm that our proposed method can generate virtual spaces reflecting user instructions with a high success rate. Additionally, we successfully identified elements contributing to the improvement in behavior generation performance through ablation study.

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。

↑