Generative early architectural visualizations: incorporating architect’s style-trained models
Journal of Computational Design and Engineering · 31.08.2024 · 11 (5) · 40-59
DOI: 10.1093/jcde/qwae065 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Computational Design and Engineering, online erschienen am 16.07.2024. Verfasst von Jin-Kook Lee und 2 weiteren Autor:innen. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 90 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: KAIA, Ministry of Land, Infrastructure and Transport, National Research Foundation of Korea.
Abstract (Originalsprache)
This study introduces a novel approach to architectural visualization using generative artificial intelligence (AI), particularly emphasizing text-to-image technology, to remarkably improve the visualization process right from the initial design phase within the architecture, engineering, and construction industry. By creating more than 10 000 images incorporating an architect’s personal style and characteristics into a residential house model, the effectiveness of base AI models. Furthermore, various architectural styles were integrated to enhance the visualization process. This method involved additional training for styles with low similarity rates, which required extensive data preparation and their integration into the base AI model. Demonstrated to be effective across multiple scenarios, this technique markedly enhances the efficiency and speed of production of architectural visualization images. Highlighting the vast potential of AI in design visualization, our study emphasizes the technology’s shift toward facilitating more user-centered and personalized design applications.
Förderung
- KAIA
- Ministry of Land, Infrastructure and Transport
- National Research Foundation of Korea
Zitieren
APA
Lee, J., Yoo, Y., & Cha, S. H. (2024). Generative early architectural visualizations: incorporating architect’s style-trained models. Journal of Computational Design and Engineering, 11(5), 40-59. https://doi.org/10.1093/jcde/qwae065
Vancouver
Lee J, Yoo Y, Cha SH. Generative early architectural visualizations: incorporating architect’s style-trained models. Journal of Computational Design and Engineering. 2024;11(5):40-59. doi:10.1093/jcde/qwae065
BibTeX
@article{Lee2024,
author = {Lee, Jin-Kook and Yoo, Youngjin and Cha, Seung Hyun},
title = {Generative early architectural visualizations: incorporating architect’s style-trained models},
journal = {Journal of Computational Design and Engineering},
year = {2024},
volume = {11},
number = {5},
pages = {40--59},
doi = {10.1093/jcde/qwae065}
}
EUVIMED