Mimarlıkta GAN’lar ve Yapay Zeka Destekli Kat Planı Tasarımı: ArchiGAN Üzerine Bir İnceleme

Abstract

Bu çalışma, yapay zekâ ve mimarlık arasındaki etkileşimi incelemek üzere ArchiGAN projesini vaka analizi olarak ele almaktadır. Generative Adversarial Networks (GAN) temelli bir yaklaşım olan ArchiGAN, apartman kat planlarının üretimini üç aşamalı bir hat üzerinden gerçekleştirmektedir: (I) bina ayak izi kütlesinin belirlenmesi, (II) programın yeniden bölümlendirilmesi ve pencere düzenlemesi, (III) mobilya yerleşimi. Bu adımların her biri, Pix2Pix tabanlı ayrı bir model aracılığıyla yürütülmekte; kullanıcı girdisiyle etkileşimli bir tasarım süreci mümkün kılınmaktadır. Çalışmada, ArchiGAN’ın mimari tasarımda makine öğreniminin uygulanabilirliğini göstermesi, insan–makines işbirliğine dayalı yeni bir paradigma önermesi ve çok birimli konut tasarımına ölçeklenebilmesi bakımından yenilikçi yönleri vurgulanmaktadır. Bununla birlikte, yük taşıyıcı elemanların sürekliliği, çıktıların raster formatında sınırlı kalması ve yüksek çözünürlüklü sonuçların elde edilememesi gibi teknik kısıtlar dikkat çekmektedir. Bulgular, GAN tabanlı yöntemlerin mimari tasarımda tek başına nihai çözüm sunmaktan ziyade, tasarımcıların sezgisel kararlarını destekleyen hibrit bir araç olarak konumlandırılabileceğini göstermektedir. Bu vaka, mimarlıkta yapay zekâ araştırmaları için hem metodolojik hem de pratik açıdan değerli bir çerçeve sunmaktadır.

Keywords

• ArchiGAN
• kat planı
• mimari tasarım
• Mimarlık ve Yapay zeka
• GAN

GANs in Architecture and AI-Assisted Floor Plan Design: An Examination of ArchiGAN

Abstract

This study examines the interaction between artificial intelligence and architecture by taking the ArchiGAN project as a case study. ArchiGAN, a Generative Adversarial Networks (GAN)-based approach, generates apartment floor plans through a three-stage pipeline: (I) defining the building footprint mass, (II) re-partitioning the program and arranging windows, and (III) furnishing layouts. Each of these steps is executed through a separate Pix2Pix-based model, enabling an interactive design process with user input. The study highlights ArchiGAN’s innovative contributions in demonstrating the applicability of machine learning to architectural design, proposing a new paradigm grounded in human–machine collaboration, and its scalability to multi-unit housing design. Nevertheless, technical limitations are evident, such as the continuity of load-bearing elements, the restriction of outputs to raster formats, and the inability to generate high-resolution results. The findings suggest that GAN-based methods should be positioned not as standalone solutions but rather as hybrid tools that support designers’ intuitive decision-making. This case study provides a valuable framework for architectural artificial intelligence research, both methodologically and practically.

Keywords

• GAN
• ArchiGAN
• Floor plan
• Architectural design
• Architecture and artificial intelligence

References

1. H. Zheng and W. Huang, "Recognition and Generation of Architectural Drawings with Machine Learning," in Proceedings of the 38th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA 2018): Recalibration – On Imprecision and Infidelity in Computational Design,
2. N. Peters, "Enabling Alternative Architectures: Collaborative Frameworks for Participatory Design," M.S. thesis, Dept. Arch., Harvard Graduate School of Design, Cambridge, MA, USA, 2017.
3. N. Martinez, "Sketching Between Humans and Artificial Intelligences," Unpublished M.S. thesis, Dept. Arch., Harvard Graduate School of Design, Cambridge, MA, USA, 2016.
4. Harapan, F., Andi, S., & Gunagama, A. F. (2021). Artificial intelligence in architectural design. International Journal of Design, 15(1), 1–6.
5. Lukovich, A. (2023). Advances in AI-based architectural design methods. International Journal of Architectural Computing, 21(3), 215–230.
6. Vergunova, N. C. (2024). The role of artificial intelligence in modern computer architecture: From algorithms to hardware optimization. Computers and Electrical Engineering. https://doi.org/10.1016/j.compeleceng.2024.107014
7. Sharma, M., Singh, A. K., & Saini, R. K. (2023). Generative AI models in architectural visualization. Journal of Computational Design, 3(4), 150–170.
8. Softaoğlu, B. (2024). The role of artificial intelligence in architectural heritage conservation. Heritage, 7(81). https://doi.org/10.3390/heritage7010081

9. Park, S., & Kim, J. (2024). Interactive use of AI tools in creative poster design generation. International Journal of Design Creativity and Innovation, 12(2), 88–103. https://doi.org/10.1080/21650349.2023.2214097
10. Radford, A., et al. (2021). DALL·E: Creating images from text. arXiv preprint. arXiv:2102.12092.
11. Wang, W., Zhang, Q., Huang, Y., & Zhang, L. (2023). Architectural façade design with style and structural features using Stable Diffusion model. Computers & Graphics, 113, 140–149. https://doi.org/10.1016/j.cag.2023.04.007
12. Smith, S., & Jones, R. (2024). Decision support systems based on AI for architectural conceptual design. Computers in Industry, 150, 103945.
13. Chen, Y., Zhao, M., & Liu, H. (2024). User-controlled AI-based architectural prototype production system. Advanced Engineering Informatics, 55, 101812. https://doi.org/10.1016/j.aei.2023.101812
14. Buldaç, M. (2024). Use of artificial intelligence tools in the experimental design process: Outcomes of a course model in interior design education. Journal of Art and Design, 14(2), 69–91. https://doi.org/10.20488/sanattasarim.1602366
15. Avinç, G. M. (2024). The use of text-to-image generation artificial intelligence tools for the production of biophilic design in architecture. Black Sea Journal of Engineering and Science, 7(3), 641–650. https://doi.org/10.34248/bsengineering.1470411
16. Yaman, D. G. K. (2025). The use of artificial intelligence tools in the early design stages of interior architecture education. International Journal of Communication and Art, 6(14), 65–78. https://doi.org/10.5281/zenodo.1234567
17. Marşoğlu, Z., & Özdemir, Ş. (2025). AI-assisted scenario visualization and storyboard development: An interior architecture studio case. Journal of the Graduate School of Natural and Applied Sciences, Istanbul Sabahattin Zaim University, 7(1), 30–39. https://doi.org/10.47769/izufbed.1633621
18. Nie, X. (2024). Exploration of Stable Diffusion in architectural design. Applied Science and Innovative Research, 8(3), 1–12. https://doi.org/10.22158/asir.v8n3p1
19. Bölek, B., Tutal, O., & Özbaşaran, H. (2023). A systematic review on artificial intelligence applications in architecture. Journal of Design for Resilience in Architecture & Planning, 4(1), 91–104. https://doi.org/10.47818/DRArch.2023.v4i1085
20. Wen, M., Liang, D., Ye, H., & Tu, H. (2024). Architectural facade design with style and structural features using stable diffusion model. Nanjing University of Aeronautics and Astronautics; La Trobe University.
21. Jin, S., Tu, H., Li, J., Fang, Y., Qu, Z., Xu, F., Liu, K., & Lin, Y. (2024). Enhancing architectural education through artificial intelligence: A case study of an AI-assisted architectural programming and design course. Buildings, 14(1), 118. https://doi.org/10.3390/buildings14010118
22. Almaz, A. F., El-Agouz, E. A. E., Abdelfatah, M. T., & Mohamed, I. R. (2024). The future role of artificial intelligence (AI) design's integration into architectural and interior design education is to improve efficiency, sustainability, and creativity. Department of Architecture Engineering, Horus University; Tanta University; Arab Academy for Science, Technology and Maritime Transport
23. Ploennigs, J., & Berger, M. (2023). AI art in architecture. AI in Civil Engineering, 2(8). https://doi.org/10.1007/s43503-023-00018-y
24. Sheikh, A. T., & Crolla, K. (2023). Architectural education with virtual reality: An exploration of Unreal Engine 5 and Nvidia Omniverse. In Proceedings of eCAADe 41 – Volume 1: Digital Design Reconsidered (pp. 159–168). Building Simplexity Lab, The University of Hong Kong.
25. Cao, Y., Gao, X., Yin, H., Yu, K., & Zhou, D. (2024). Reimagining tradition: A comparative study of artificial intelligence and virtual reality in sustainable architecture education. Sustainability, 16(24), 11135. https://doi.org/10.3390/su162411135
26. Mammadov, E., Asgarov, A., & Mammadova, A. (2025). The role of artificial intelligence in modern computer architecture: From algorithms to hardware optimization. Portuni, 1(2), Article 010208. https://doi.org/10.69760/portuni.010208
27. Yaşar, I., Arslan Selçuk, S., & Alaçam, S. (2025). Use of artificial intelligence and prompt literacy in architectural education. New Design Ideas, 9(1), 248–268. https://doi.org/10.62476/ndi.91.24
28. Abd El-Maksoud, N. M., & Ahmed, E. A. (2024). Artificial intelligence applications in green architecture. Journal of Fayoum University Faculty of Engineering, 7(2), 317–337. https://doi.org/10.21608/fuje.2024.345049
29. Li, Y., Chen, H., Yu, P., & Yang, L. (2025). A review of artificial intelligence applications in architectural design: Energy-saving renovations and adaptive building envelopes. Energies, 18(4), 918. https://doi.org/10.3390/en18040918
30. Dorsey, J., Xu, S., Smedresman, G., Rushmeier, H., & McMillan, L. (2007). The Mental Canvas: A tool for conceptual architectural design and analysis. 15th Pacific Conference on Computer Graphics and Applications, 201–210. IEEE. https://doi.org/10.1109/PG.2007.64
31. P. Isola, J.-Y. Zhu, T. Zhou, and A. A. Efros, "Image-to-image translation with conditional adversarial networks," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, July 21–26, 2017. Piscataway, NJ: IEEE, 2017. doi: 10.48550/arXiv.1611.07004.
32. NVIDIA, "NVIDIA Developer," NVIDIA Corporation, 2025. [Online]. Available: https://developer.nvidia.com/. [Accessed: Aug. 01, 2025].