Volume 15, Issue 1 (2025)
Naqshejahan 2025, 15(1): 1-26 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Sadri S A, Kaboli M, Mirzarezaee M, Soleymani M. Applying Latent Diffusion Model - Architecture as a Model for the generation of Architecture Documents (Morphogenesis Patterns of Residential Plan). Naqshejahan 2025; 15 (1) :1-26
URL: http://bsnt.modares.ac.ir/article-2-75289-en.html
URL: http://bsnt.modares.ac.ir/article-2-75289-en.html
1- Department of Architecture, Faculty of Art and Architecture, West Tehran Branch, Islamic Azad University, Tehran, Iran.
2- Department of Architecture, Faculty of Art and Architecture, Damavand branch, Islamic Azad University, Damavand, Iran. ,hadikaboli@gmail.com
3- Department of Computer Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran.
2- Department of Architecture, Faculty of Art and Architecture, Damavand branch, Islamic Azad University, Damavand, Iran. ,
3- Department of Computer Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran.
Abstract: (715 Views)
Aims: Morphogenesis layout of the architectural space is one of the first and longest steps in the work process of architects to accomplish their tasks. It is thus that the designing procedure has taken a lot of time and effort up to now. The purpose of this study was to provide a new model for morphogenesis of architecture documents. It specifically created residential building plans by means of neural networks.
Methods: The computational approach of this model was a Latent Diffusion Model including three neural networks: a noise reduction network (UNET), an external variational auto encoder network (VAE), and a constraint encoder network (Clip). A fine-tuning mechanism was used to train this practical model. The method of conducting this study was based on computer simulation, using Python programming language.
Findings: The researchers used the criteria of Principal component analysis )PCA( and a support vector machine )SVM( while evaluating the findings quantitatively and qualitatively. Reading of samples indicated that the workflow and the proposed model of the research not only significantly improved in generating floor plans, compared to the current methods, but also the project plans, in many cases, were comparable with those of humans.
Conclusion: The researchers used the criteria of PCA and SVM while evaluating the findings quantitatively and qualitatively. The researchers’ samples indicated that the workflow and the proposed model of the study significantly improved in generating floor plans, compared to the current methods. Besides, in many cases, the project plans were comparable with those of humans
Methods: The computational approach of this model was a Latent Diffusion Model including three neural networks: a noise reduction network (UNET), an external variational auto encoder network (VAE), and a constraint encoder network (Clip). A fine-tuning mechanism was used to train this practical model. The method of conducting this study was based on computer simulation, using Python programming language.
Findings: The researchers used the criteria of Principal component analysis )PCA( and a support vector machine )SVM( while evaluating the findings quantitatively and qualitatively. Reading of samples indicated that the workflow and the proposed model of the research not only significantly improved in generating floor plans, compared to the current methods, but also the project plans, in many cases, were comparable with those of humans.
Conclusion: The researchers used the criteria of PCA and SVM while evaluating the findings quantitatively and qualitatively. The researchers’ samples indicated that the workflow and the proposed model of the study significantly improved in generating floor plans, compared to the current methods. Besides, in many cases, the project plans were comparable with those of humans
Keywords: Morphogenesis, Spatial Layout, Automated Plan Generation, Neural Networks, Latent Diffusion Model, AI, Digital Architecture
Article Type: Original Research |
Subject:
Highperformance Architecture
Received: 2024/05/24 | Accepted: 2024/08/26 | Published: 2025/04/30
Received: 2024/05/24 | Accepted: 2024/08/26 | Published: 2025/04/30
References
1. Shekhawat K, Pinki N, Duarte JP. A graph theoretical approach for creating building floor plans. In: Communications in computer and information science. 2019. p. 3–14. https://doi.org/10.1007/978-981-13-8410-3_1 [Article] [DOI]
2. Grason J. An approach to computerized space planning using graph theory. In: Proceedings of the 8th Design Automation Workshop. Association for Computing Machinery New York; 1971. p. 170–8. https://doi.org/10.1145/800158.805070 [Article] [DOI]
3. Alexander C. Notes on the synthesis of form. Harvard University Press; 1964. Available at: https://books.google.com.om/books?hl=en&lr=&id=Kh3T3XFUfPQC&oi=fnd&pg=PA1&dq=Alexander+C.+Notes+on+the+synthesis+of+form.+Harvard+University+Press%3B+1964.&ots=_F22JzknHA&sig=H7QUhL52gz6TqOitTOT0D9rofAU&redir_esc=y#v=onepage&q=Alexander%20C.%20Notes%20on%20the%20synthesis%20of%20form.%20Harvard%20University%20Press%3B%201964.&f=false [Article]
4. Stiny G, Mitchell WJ. The Palladian grammar. Environment and Planning B Planning and Design. 1978 Jan 1;5(1):5–18. https://doi.org/10.1068/b050005 [Article] [DOI]
5. Çaǧdaş G. A shape grammar model for designing row-houses. Design Studies. 1996 Jan 1;17(1):35–51. https://doi.org/10.1016/0142-694x(95)00005-c [Article] [DOI]
6. Eastman CM. Automated space planning. Artificial Intelligence. 1973 Jan 1;4(1):41–64. https://doi.org/10.1016/0004-3702(73)90008-8 [Article] [DOI]
7. Rahbar M, Bemanian M, Davaei Markazi A. Training CGAN Algorithm for Generating Architectural Layout Heat Map. Armanshahr Architecture & Urban Development Journal [Internet]. 2020 Nov 21;13(32):131–42. https://www.doi.org/10.22034/aaud.2020.154406.1717 [Article] [DOI]
8. Aalaei M, Saadi M, Rahbar M, Ekhlassi A. Architectural layout generation using a graph-constrained conditional Generative Adversarial Network (GAN). Automation in Construction. 2023 Nov 1;155:105053. https://doi.org/10.1016/j.autcon.2023.105053 [Article] [DOI]
9. Nauata N, Chang KH, Cheng CY, Mori G, Furukawa Y. House-GAN: Relational Generative Adversarial Networks for graph-constrained House Layout Generation. arXiv (Cornell University). 2020 Jan 1; https://doi.org/10.48550/arXiv.2003.06988 [Article] [DOI]
10. Nauata N, Hosseini S, Chang KH, Chu H, Cheng CY, Furukawa Y. House-GAN++: Generative Adversarial Layout Refinement Networks. arXiv (Cornell University). 2021 Jan 1. https://doi.org/10.48550/arXiv.2103.02574 [Article] [DOI]
11. Wu W, Fu XM, Tang R, Wang Y, Qi YH, Liu L. Data-driven interior plan generation for residential buildings. ACM Transactions on Graphics. 2019 Nov 8;38(6):1–12. https://doi.org/10.1145/3355089.3356556 [Article] [DOI]
12. Zawidzki M, Tateyama K, Nishikawa I. The constraints satisfaction problem approach in the design of an architectural functional layout. Engineering Optimization. 2011 Sep 1;43(9):943–66. https://doi.org/10.1080/0305215x.2010.527005 [Article] [DOI]
13. Dino IG. An evolutionary approach for 3D architectural space layout design exploration. Automation in Construction. 2016 Sep 1;69:131–50. https://doi.org/10.1016/j.autcon.2016.05.020 [Article] [DOI]
14. Yeh IC. Architectural layout optimization using annealed neural network. Automation in Construction. 2006 Jul 1;15(4):531–9. https://doi.org/10.1016/j.autcon.2005.07.002 [Article] [DOI]
15. Gero JS, Kazakov VA. Evolving design genes in space layout planning problems. Artificial Intelligence in Engineering. 1998 Jul 1;12(3):163–76. https://doi.org/10.1016/s0954-1810(97)00022-8 [Article] [DOI]
16. Yi H. User-driven automation for optimal thermal-zone layout during space programming phases. Architectural Science Review. 2015 Apr 2;59(4):279–306. https://doi.org/10.1080/00038628.2015.1021747 [Article] [DOI]
17. Guo Z, Li B. Evolutionary approach for spatial architecture layout design enhanced by an agent-based topology finding system. Frontiers of Architectural Research. 2017 Mar 1;6(1):53–62. https://doi.org/10.1016/j.foar.2016.11.003 [Article] [DOI]
18. Fortin G. BUBBLE: Relationship diagrams using iterative vector approximation. Design Automation Conference. 1978 Jun 19;145–51. https://dl.acm.org/citation.cfm?id=803079 [Article]
19. Arvin SA, House DH. Modeling architectural design objectives in physically based space planning. Automation in Construction . 2002 Feb 1;11(2):213–25. https://doi.org/10.1016/s0926-5805(00)00099-6 [Article] [DOI]
20. Chatzikonstantinou I. A 3-Dimensional Architectural Layout Generation Procedure for optimization applications : DC-RVD. eCAADe Proceedings. 2014 Jan 1; https://doi.org/10.52842/conf.ecaade.2014.1.287 [Article] [DOI]
21. AlOmani A, El-Rayes K. Automated generation of optimal thematic architectural layouts using image processing. Automation in Construction . 2020 Sep 1;117:103255. https://doi.org/10.1016/j.autcon.2020.103255
22. Keshavarzi M, Rahmani-Asl M. GenFloor: Interactive generative space layout system via encoded tree graphs. Frontiers of Architectural Research . 2021 Dec 1;10(4):771–86. https://doi.org/10.1016/j.foar.2021.07.003 [Article] [DOI]
23. Koenig R, Knecht K. Comparing two evolutionary algorithm based methods for layout generation: Dense packing versus subdivision. Artificial Intelligence for Engineering Design Analysis and Manufacturing. 2014 Jul 22;28(3):285–99. https://doi.org/10.1017/s0890060414000237 [Article] [DOI]
24. Ruch J. Interactive Space Layout: A Graph Theoretical Approach. In: 15th Design Automation Conference. IEEE; 1978. p. 152–7. https://doi.org/10.1109/dac.1978.1585162 [Article] [DOI]
25. Wong SSY, Chan KCC. EvoArch: An evolutionary algorithm for architectural layout design. Computer-Aided Design . 2009 Sep 1;41(9):649–67. https://doi.org/10.1016/j.cad.2009.04.005 [Article] [DOI]
26. Roth J, Hashimshony R. Algorithms in graph theory and their use for solving problems in architectural design. Computer-Aided Design. 1988 Sep 1;20(7):373–81. https://doi.org/10.1016/0010-4485(88)90214-x [Article] [DOI]
27. Lobos D, Trebilcock M. Informação de desempenho de um edifício e gráficos de abordagem na concepção de projetos. Arquitetura Revista. 2014 Aug 4;10(1). https://doi.org/10.4013/arq.2014.101.03 [Article] [DOI]
28. Verma M, Thakur MK. Architectural space planning using Genetic Algorithms. In: 2010 The 2nd International Conference on Computer and Automation Engineering (ICCAE). IEEE; 2010. p. 268–75. https://doi.org/10.1109/iccae.2010.5451497 [Article] [DOI]
29. Schwarz A, Berry DM, Shaviv E. On the use of the automated building design system. Computer-Aided Design. 1994 Oct 1;26(10):747–62. https://doi.org/10.1016/0010-4485(94)90013-2 [Article] [DOI]
30. Medjdoub B, Yannou B. Separating topology and geometry in space planning. Computer-Aided Design. 2000 Jan 1;32(1):39–61. https://doi.org/10.1016/s0010-4485(99)00084-6 [Article] [DOI]
31. Nagy D, Lau D, Locke J, Stoddart J, Villaggi L, Wang R, et al. Project Discover: An application of Generative Design for Architectural Space planning. In: SIMAUD ’17: Proceedings of the Symposium on Simulation for Architecture and Urban Design. Society for Computer Simulation International San Diego, CA, United States; 2017. p. 1–8. https://doi.org/10.22360/simaud.2017.simaud.007 [Article] [DOI]
32. Rodrigues E, Gaspar AR, Gomes Ál. An evolutionary strategy enhanced with a local search technique for the space allocation problem in architecture, Part 1: Methodology. Computer-Aided Design. 2013 May 1;45(5):887–97. https://doi.org/10.1016/j.cad.2013.01.001 [Article] [DOI]
33. Babakhani R. The machine learning process in applying spatial relations of residential plans based on samples and adjacency matrix. Maremat & Memari-e Iran. 2023;13(34). http://mmi.aui.ac.ir/article-1-1297-fa.html [Article]
34. Sadri A, Mirzarezaee M, Soleimani M. Analyzing methods and approaches to produce automatic space layouts. Memarshahr. 2023;1(1):90–117. https://sanad.iau.ir/fa/Article/1041419 [Article]
35. Goodfellow IJ, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, et al. Generative adversarial networks. arXiv (Cornell University) . 2014 Jan 1; https://doi.org/10.48550/arxiv.1406.2661
36. Sohl-Dickstein J, Weiss EA, Maheswaranathan N, Ganguli S. Deep Unsupervised Learning using Nonequilibrium Thermodynamics. arXiv.org. 2015. https://doi.org/10.48550/arXiv.1503.03585 [Article] [DOI]
37. Chaillou S. ArchiGAN: Artificial Intelligence x Architecture. In: Architectural Intelligence. 2020. p. 117–27. https://doi.org/10.1007/978-981-15-6568-7_8 [Article] [DOI]
38. Hu R, Huang Z, Tang Y, Van Kaick O, Zhang H, Huang H. Graph2Plan. ACM Transactions on Graphics. 2020 Aug 12;39(4). https://doi.org/10.1145/3386569.3392391 [Article] [DOI]
39. Huang W, Zheng H. Architectural Drawings Recognition and Generation through Machine Learning. ACADIA Quarterly . 2018 Jan 1; https://doi.org/10.52842/conf.acadia.2018.156 [Article] [DOI]
40. Rombach R, Blattmann A, Lorenz D, Esser P, Ommer B. High-Resolution Image Synthesis with Latent Diffusion Models. arXiv (Cornell University). 2021 Jan 1; https://doi.org/10.48550/arxiv.2112.10752 [Article] [DOI]
41. Ruiz N, Li Y, Jampani V, Pritch Y, Rubinstein M, Aberman K. DreamBooth: Fine Tuning Text-to-Image diffusion models for Subject-Driven Generation. arXiv (Cornell University). 2022 Jan 1; https://doi.org/10.48550/arXiv.2208.12242 [Article] [DOI]
42. Radford A, Kim JW, Hallacy C, Ramesh A, Goh G, Agarwal S, et al. Learning transferable visual models from natural language supervision. arXiv (Cornell University) . 2021 Jan 1; https://doi.org/10.48550/arXiv.2103.00020 [Article] [DOI]
43. Fakhr BV, Mahdavinejad M, Rahbar M, Dabaj B. Design Optimization of the Skylight for Daylighting and Energy Performance Using NSGA-II. Journal of Daylighting. 2023 May 23;10(1):72-86. https://doi.org/10.15627/jd.2023.6 Available at: https://solarlits.com/jd/10-72 [Article] [DOI]
44. Rahbar M, Mahdavinejad M, Bemanian M, Davaie Markazi AH, Hovestadt L. Generating Synthetic Space Allocation Probability Layouts Based on Trained Conditional-GANs. Applied Artificial Intelligence. 2019 Jul 3;33(8):689-705. https://doi.org/10.1080/08839514.2019.1592919. Available at: https://www.tandfonline.com/doi/full/10.1080/08839514.2019.1592919 [Article] [DOI]
45. Rahbar M, Mahdavinejad M, Bemanian M, Davaie-Markazi A. Generating space layout heat maps with cGAN algorithms in artificial intelligence. Armanshahr Architecture & Urban Development. 2020;13(32):131-142. https://doi.org/10.22034/aaud.2020.154406.1717 [Article] [DOI]
46. Rahbar M, Mahdavinejad, M, Bemanian, M, Davaie-Markazi, A. Artificial neural network for outlining and predicting environmental sustainable parameters. Journal of Sustainable Architecture and Urban Design. 2020;7(2):169-182. https://doi.org/10.22061/jsaud.2019.4501.1333 [Article] [DOI]
47. Rahbar M, Mahdavinejad M, Markazi A.H.D., Bemanian M. Architectural layout design through deep learning and agent-based modeling: A hybrid approach. Journal of Building Engineering. 2022 April15; 47, 103822. https://doi.org/10.1016/j.jobe.2021.103822. Available at: https://www.sciencedirect.com/science/article/abs/pii/S2352710221016806?via%3Dihub [Article] [DOI]
48. Esmaeilian Toussi H, Etesam I, Mahdavinejad M. The Application of Evolutionary Algorithms and Shape Grammar in the Design Process Based upon Traditional Structures. The Monthly Scientific Journal of Bagh-e Nazar, 2021 May;18(95):19-36. https://doi.org/10.22034/BAGH.2019.161797.3914 [Article] [DOI]
49. Goharian A, Daneshjoo K, Shaeri J, Mahdavinejad M, Yeganeh M. A designerly approach to daylight efficiency of central light-well; combining manual with NSGA-II algorithm optimization. Energy. 2023 Apr 17:127402. https://doi.org/10.1016/j.energy.2023.127402 Available at: https://www.sciencedirect.com/science/article/abs/pii/S036054422300796X?via%3Dihub [Article] [DOI]
50. Mardomi K, Soheilifard M, Aghaazizi M. Integration of Architecture & Structure in Optimizing Supports’ Location Using Genetic Algorithm Method; Case Study: Cladding based on Iranian Girih. Naqshejahan - Basic Studies and New Technologies of Architecture and Planning. 2015 Jun 10;5(2):65-75. [Persian] https://dorl.net/dor/20.1001.1.23224991.1394.5.2.3.6 [Article]
51. Mardomi K, Moodi A. Agent-Based Modeling; a Paradigm to Deal with Complexity and Uncertainty in Architectural and Environmental Problems. Naqshejahan - Basic studies and New Technologies of Architecture and Planning. 2019 Sep 10;9(2):145-55. [Persian] https://dorl.net/dor/20.1001.1.23224991.1398.9.2.1.2 [Article]
52. Tadayon K, Mahdavinejad M, Shahcheraghi A. Advanced mathematical algorithms to outline integrated architectural design process. Journal of Sustainable Architecture and Urban Design. 2021 Aug 23;9(1):1-12. https://doi.org/10.22061/JSAUD.2020.6603.1686 [Article] [DOI]
53. Tadayon K, Mahdavinejad M, Shahcheraghi A. Application of Machine Learning Methodology in the Design of the Built Environment. Urban Design Discourse: A Review of Contemporary Literatures and Theories. 2024; 5(2): 116-128. Available at: http://udd.modares.ac.ir/article-40-75893-fa.html [Article]
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |