Abstract
This paper introduces a novel method for generating architectural floor plans using Conditional Large Diffusion Models to migrate the limitations of existing generative methods, such as restrictions on rectilinear configurations, limited scalabilities, and the simplicity of details. Central to this study is the development of a large-scale dataset comprising high-quality floor plan images with corresponding condition maps and textual captions. The essential step is to setup the conditions in relative to the architectural floor plan. The data collection and processing align with these condition requirements. The development of the dataset includes manual preparation of 1007 floor plan images as an initial set for training the floor plan recognition models that facilitate the automated annotation, algorithmic generation of the 12000 images with Grasshopper as a supplementary pseudo set for testing the generation effectiveness, and several image captioning and visual question-answering models for producing textural descriptions. The generation models trained on this dataset demonstrates the potential to produce diverse planning options using basic constraints as the conditions, which was evaluated by several user studies. The findings underscore the transformative potential of integrating advanced generative AI technologies in architectural design.
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
Lynch, K.: The Image of the City. Cambridge, M.I.T. Press (2008)
Eastman, C.: The Use of Computers Instead of Drawings in Building Design. AIA J. 63 (1975)
Friedman, Y., Derix, C.: The Flatwriter: Choice by Computer. Progressive Architecture (1971)
Flemming, U.: On the representation and generation of loosely packed arrangements of rectangles. Environ. Plann. B Plann. Des. 13, 189–205 (1986). https://doi.org/10.1068/b130189
Koning, H., Eizenberg, J.: The language of the Prairie: Frank Lloyd Wright’s Prairie houses. Environ. Plann. B Plann. Des. 8, 295–323 (1981). https://doi.org/10.1068/b080295
Stiny, G.: Introduction to Shape and Shape Grammars
Stiny, G., Mitchell, W.J.: The Palladian grammar. Environ. Plann. B. 5, 5–18 (1978). https://doi.org/10.1068/b050005
Baušys, R., Pankrašovaite, I.: Optimization of architectural layout by the improved genetic algorithm. J. Civil Eng. Manag. 11, 13–21 (2005). https://doi.org/10.3846/13923730.2005.9636328
Thakur, M.K., Kumari, M., Das, M.: Architectural layout planning using genetic algorithms. In: 2010 3rd International Conference on Computer Science and Information Technology, pp. 5–11 (2010). https://doi.org/10.1109/ICCSIT.2010.5565165.
Weber, R.E., Mueller, C., Reinhart, C.: Automated floorplan generation in architectural design: a review of methods and applications. Automat. Construct. 140, 104385 (2022). https://doi.org/10.1016/j.autcon.2022.104385
Retsin, G.: Toward discrete architecture: automation takes command. Presented at the ACADIA 2019: Ubiquity and Autonomy, Austin (2019). https://doi.org/10.52842/conf.acadia.2019.532.
Gumin, M.: Wave Function Collapse Algorithm (2016). https://github.com/mxgmn/WaveFunctionCollapse
Hosmer, T., Tigas, P., Reeves, D., He, Z.: Spatial assembly with self-play reinforcement learning. In: Distributed Proximities, Acadia 2020 Proceedings, p. 12 (2020)
Marson, F., Musse, S.R.: Automatic real-time generation of floor plans based on squarified treemaps algorithm. Int. J. Comput. Games Technol. 2010, 1–10 (2010). https://doi.org/10.1155/2010/624817
Wu, W., Fan, L., Liu, L., Wonka, P.: MIQP-based layout design for building interiors. Comput. Graph. Forum. 37, 511–521 (2018). https://doi.org/10.1111/cgf.13380
Chaillou, S.: ArchiGAN: Artificial intelligence x architecture. In: Yuan, P.F., Xie, M., Leach, N., Yao, J., Wang, X. (eds.) Architectural Intelligence: Selected Papers from the 1st International Conference on Computational Design and Robotic Fabrication (CDRF 2019), pp. 117–127. Springer, Singapore (2020). https://doi.org/10.1007/978-981-15-6568-7_8
Kalervo, A., Ylioinas, J., Häikiö, M., Karhu, A., Kannala, J.: CubiCasa5K: A Dataset and an Improved Multi-task Model for Floorplan Image Analysis. arXiv preprint arXiv:1904.01920 (2019)
Wu, W., Fu, X.-M., Tang, R., Wang, Y., Qi, Y.-H., Liu, L.: Data-driven interior plan generation for residential buildings. ACM Trans. Graph. 38, 1–12 (2019). https://doi.org/10.1145/3355089.3356556
Gozalo-Brizuela, R., Garrido-Merchan, E.C.: ChatGPT is not all you need. A State of the Art Review of large Generative AI Models. arXiv preprint arXiv:2301.04655 (2023)
runwayml/stable-diffusion-v1-5 · Hugging Face. https://huggingface.co/runwayml/stable-diffusion-v1-5. Accessed 08 May 2023
Midjourney. https://www.midjourney.com/home/. Accessed 10 Sept 2023
Zhang, L., Agrawala, M.: Adding Conditional Control to Text-to-Image Diffusion Models. arXiv preprint arXiv:2302.05543 (2023). https://doi.org/10.48550/arXiv.2302.05543.
He, Z., Li, X., Fan, L., Wang, H.J.: Revamping interior design workflow through generative artificial intelligence. In: Stephanidis, C., Antona, M., Ntoa, S., and Salvendy, G. (eds.) HCI International 2023 Posters, pp. 607–613. Springer, Cham (2023). https://doi.org/10.1007/978-3-031-36001-5_78
Ronneberger, O., Fischer, P., Brox, T.: U-Net: Convolutional Networks for Biomedical Image Segmentation. arXiv preprint arXiv:1505.04597 (2015)
PlanFinder. https://www.planfinder.xyz/. Accessed 29 Aug 2023
Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models, arXiv preprint arXiv:2301.12597 (2023). https://doi.org/10.48550/arXiv.2301.12597
Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models. arXiv preprint arXiv:2304.10592 (2023)
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 paper
Cite this paper
He, Z. et al. (2024). Generating Architectural Floor Plans Through Conditional Large Diffusion Model. In: Stephanidis, C., Antona, M., Ntoa, S., Salvendy, G. (eds) HCI International 2024 Posters. HCII 2024. Communications in Computer and Information Science, vol 2120. Springer, Cham. https://doi.org/10.1007/978-3-031-62110-9_6
Download citation
DOI: https://doi.org/10.1007/978-3-031-62110-9_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-62109-3
Online ISBN: 978-3-031-62110-9
eBook Packages: Computer ScienceComputer Science (R0)