arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2404.13353cs.CV
收藏

通过扩散模型生成采光驱动的建筑设计

Generating Daylight-driven Architectural Design via Diffusion Models

Tsinghua University(清华大学);Shenzhen University(深圳大学)

Pengzhi Li, Baijuan Li

AI总结:

本文提出一种采光驱动的AI辅助建筑设计方法,结合大规模语言模型与文本到图像模型,快速生成建筑体量与立面窗户布局,提升设计渲染效率并支持建筑师创作灵感。

摘要:

近年来,大规模模型的快速发展为建筑等跨学科领域带来了新的可能性。本文提出了一种新颖的采光驱动的AI辅助建筑设计方法。首先,我们提出一种体量模型生成方法,利用随机参数快速生成建筑体量模型。随后,我们集成了采光驱动的立面设计策略,准确确定窗户布局并将其应用于体量模型。最后,我们将大规模语言模型与文本到图像模型无缝结合,提升了生成可视化建筑设计渲染图的效率。实验结果表明,我们的方法支持建筑师的创作灵感,并为建筑设计发展开辟了新途径。项目页面:https://zrealli.github.io/DDADesign/.

英文摘要:

In recent years, the rapid development of large-scale models has made new possibilities for interdisciplinary fields such as architecture. In this paper, we present a novel daylight-driven AI-aided architectural design method. Firstly, we formulate a method for generating massing models, producing architectural massing models using random parameters quickly. Subsequently, we integrate a daylight-driven facade design strategy, accurately determining window layouts and applying them to the massing models. Finally, we seamlessly combine a large-scale language model with a text-to-image model, enhancing the efficiency of generating visual architectural design renderings. Experimental results demonstrate that our approach supports architects' creative inspirations and pioneers novel avenues for architectural design development. Project page: https://zrealli.github.io/DDADesign/.

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。

↑