Abstract
This research explores the applicability of image generation artificial intelligence (image gen AI) techniques for diverse design visualisation within the field of architecture. In architecture, images of building exteriors and interior spaces are commonly used as reference images for design and communication purposes, particularly in the early stages of design planning. However, generating a single image involves a complex process and requires significant time, economic and human resources. To address this challenge, this chapter proposes an approach that efficiently generates reference images for interior spaces, building facades, and building forms using image-generation (“image gen”) AI. Based on the image gen AI, the process of this study consists of two main stages: (1) Intensive Test of the Default Model (2) Model Fine-Tuning Process. Within this framework, the architectural focus of this research covers four aspects: (1) Generating indoor space images with diverse design styles, (2) Designing bathroom spatial layouts based on users’ physical and medical characteristics, (3) Creating facade designs that capture regional characteristics, and (4) Generating housing images that reflect various renowned architects’ design styles. Through these efforts, the research demonstrates the potential of AI in the field of architecture and contributes to the advancement of architectural image generation research.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Borden I (2007) Imaging architecture: the uses of photography in the practice of architectural history. J Archit 12(1):57–77. https://doi.org/10.1080/13602360701217989
Chiu M-L (1995) Collaborative design in CAAD studios: shared ideas, resources, and representations. In: Proceedings of international conference on CAAD future, pp 749–759
Farsäter K, Olander S (2019) Early decision-making for school building renovation. Facilities 37(13/14):981–994. https://doi.org/10.1108/F-10-2017-0102
Hu EJ, Shen Y, Wallis P, Allen-Zhu Z, Li Y, Wang S, Wang L, Chen W (2021) Lora: low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685. https://doi.org/10.48550/arXiv.2106.09685
Kalay YE (2004) Architecture’s new media: principles, theories, and methods of computer-aided design. MIT press
Kim J-S, Lee J-K (2020) Stochastic detection of interior design styles using a deep-learning model for reference images. Appl Sci 10(20):7299. https://doi.org/10.3390/app10207299
Kim J-S, Choi J-S, Lee J-K (2019) Approach to design reference management using auto-recognition system of room and design style. Int J Eng Technol (UAE) 8(1.4):56–64. https://doi.org/10.14419/ijet.v8i1.4.25133
Lee H, Shin J, Lee J-K (2016) BIM-enabled definition of a path object and its properties to evaluate building circulation using numerical data. J Asian Archit Build Eng 15(3):425–432. https://doi.org/10.3130/jaabe.15.425
Lee J-K, Shin J, Lee Y (2020) Circulation analysis of design alternatives for elderly housing unit allocation using building information modelling-enabled indoor walkability index. Indoor Built Environ 29(3):355–371. https://doi.org/10.1177/1420326X18763892
Merkel J (2008) SANAA’s new museum of contemporary art, New York. Archit Des 78(3):98–101. https://doi.org/10.1002/ad.684
Oppenlaender J (2022) The creativity of text-to-image generation. In: Proceedings of the 25th international academic mindtrek conference, pp 192–202
Phare DM, Gu N, Ostwald M (2018) Representation in design communication: meaning-making in a collective context. Front Built Environ 4:36. https://doi.org/10.3389/fbuil.2018.00036
Ramesh A, Pavlov M, Goh G, Gray S, Voss C, Radford A, Sutskever I (2021) Zero-shot text-to-image generation. In: International conference on machine learning. PMLR 139:8821–8831
Ramesh A, Dhariwal P, Nichol A, Chu C, Chen M (2022) Hierarchical text-conditional image generation with clip latents 1(2):3. arXiv preprint arXiv:2204.06125
Rombach R, Blattmann A, Lorenz D, Esser P, Ommer B (2022) High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR), pp 10684–10695
Saharia C, Chan W, Saxena S, Li L, Whang J, Denton EL, Ghasemipour K, Lopes G, Raphael KA, Burcu S, Tim H, Jonathan F, David J, Norouzi M (2022) Photorealistic text-to-image diffusion models with deep language understanding. Adv Neural Inf Process Syst 35:36479–36494
Sharifi Noorian S, Qiu S, Psyllidis A, Bozzon A, Houben G-J (2020) Detecting, classifying, and mapping retail storefronts using street-level imagery. In: Proceedings of the 2020 international conference on multimedia retrieval, pp 495–501
Shin J, Lee J-K (2019) Indoor walkability index: BIM-enabled approach to quantifying building circulation. Autom Constr 106:102845. https://doi.org/10.1016/j.autcon.2019.102845
Sun C, Zhou Y, Han Y (2022) Automatic generation of architecture facade for historical urban renovation using generative adversarial network. Build Environ 212:108781. https://doi.org/10.1016/j.buildenv.2022.108781
Vandenbulcke B (2013) Concretion, abstraction: the place of design processes in today architecture practice. Case study: Sanaa. International conference on architecture and urban design
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. Advances in neural information processing systems, p 30
Vimpari V, Kultima A, Hämäläinen P, Guckelsberger C (2023) “An adapt-or-die type of situation”: perception, adoption, and use of text-to-image-generation AI by game industry professionals. arXiv preprint arXiv:2302.12601. https://doi.org/10.48550/arXiv.2302.12601
Acknowledgements
This work was supported in 2023 by the Korea Agency for Infrastructure Technology Advancement (KAIA) grant funded by the Ministry of Land, Infrastructure and Transport (Grant RS-2021-KA163269). This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MIST) (No. NRF-2022R1A2C1093310).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Lee, JK. et al. (2024). How to Enhance Architectural Visualisation Using Image Gen AI. In: Lee, J.H., Ostwald, M.J., Kim, M.J. (eds) Multimodality in Architecture. Springer, Cham. https://doi.org/10.1007/978-3-031-49511-3_9
Download citation
DOI: https://doi.org/10.1007/978-3-031-49511-3_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-49510-6
Online ISBN: 978-3-031-49511-3
eBook Packages: EngineeringEngineering (R0)