EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Automating computational design with generative AI

Joern Ploennigs, Markus Berger

Civil Engineering Design · 2024-07 · 6 (2) · 41-52

DOI: 10.1002/cend.202400006 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Civil Engineering Design, online erschienen am 17.07.2024. Verfasst von Joern Ploennigs und 1 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

AI image generators based on diffusion models have recently garnered attention for their capability to create images from simple text prompts. However, for practical use in civil engineering they need to be able to create specific construction plans for given constraints. This paper investigates the potential of current AI generators in addressing such challenges, specifically for the creation of simple floor plans. We explain how the underlying diffusion‐models work and propose novel refinement approaches to improve semantic encoding and generation quality. In several experiments we show that we can improve validity of generated floor plans from 6% to 90%. Based on these results we derive future research challenges considering building information modeling. With this we provide: (i) evaluation of current generative AIs; (ii) propose improved refinement approaches; (iii) evaluate them on various examples; (iv) derive future directions for diffusion models in civil engineering.

Zitieren

APA

Ploennigs, J., & Berger, M. (2024). Automating computational design with generative AI. Civil Engineering Design, 6(2), 41-52. https://doi.org/10.1002/cend.202400006

Vancouver

Ploennigs J, Berger M. Automating computational design with generative AI. Civil Engineering Design. 2024;6(2):41-52. doi:10.1002/cend.202400006

BibTeX
@article{Ploennigs2024,
  author = {Ploennigs, Joern and Berger, Markus},
  title = {Automating computational design with generative AI},
  journal = {Civil Engineering Design},
  year = {2024},
  volume = {6},
  number = {2},
  pages = {41--52},
  doi = {10.1002/cend.202400006}
}
Kostenlos starten →