An Approach to Spatial Design Visualization through Design Style Combinations Based on Image-Generation AI

Hyun Jeong; Jin-Kook Lee

doi:10.6107/JKHA.2023.34.6.017

All Issue

2023 Vol.34, Issue 6 Preview Page Next Page

Research Article

An Approach to Spatial Design Visualization through Design Style Combinations Based on Image-Generation AI 이미지 생성 AI 기반 디자인 스타일 조합을 통한 실내 공간 디자인 시각화의 새로운 접근 방법 제안

25 December 2023. pp. 017-024

PDF XML

Abstract

This paper explores the use of generative artificial intelligence, particularly Image-Generation AI (Image-Gen AI), in the field of interior architectural space visualization. The focus is on automating spatial design visualization based on design styles and examining practical applications. Interior space visualization involves a complex process that harmonizes visual aspects with functionality and user experience, making effective visualization crucial for communication among stakeholders. Unlike conventional methods limited by expertise, costs, and time, Image-Gen AI has the potential to automate design elements like styles, components, and spatial arrangements to enhance visualization. The study fine-tuned Image-Gen AI’s Base Model for specific design styles, enabling spatial visualization image generation using Text-to-Image and Image-to-Image methods. Results showed that the fine-tuned model effectively represented design styles not well captured by the base model, producing high-quality images. This suggests that design styles have unique features influenced by culture, region, and user preferences. By fine-tuning Image-Gen AI, a wide range of applications for creating customized designs considering these aspects can be inferred. This approach enhances spatial design by accommodating style diversity and user preferences, facilitating practical design comparisons. Additionally, the study proposes applying this approach beyond architecture to achieve effective visualization in diverse domains.

Keywords

Architectural Design

Indoor Design Style

Image-Generation AI

Fine-tuned Model

키워드

건축 디자인

실내디자인 스타일

이미지 생성 인공지능

추가 학습 모델

References

Ah-Soon, C., & Tombre, K. (1997). Variations on the analysis of architectural drawings. In Proceedings of the fourth international conference on document analysis and recognition, Vol. 1 (pp. 347-351), IEEE. 10.1109/ICDAR.1997.619869

Archdaily (2023). Architectural Trend. Retrieved from https://www.archdaily.com/

Cherneff, J., Logcher, R., Connor, J., & Patrikalakis, N. (1992). Knowledge-based interpretation of architectural drawings. Research in Engineering Design, 3, 195-210. 10.1007/BF01580842

Ching, Francis D. K. (2011). A visual dictionary of architecture: John Wiley & Sons.

Chiu, M. L. (1995). Collaborative design in CAAD studios: shared ideas, resources, and representations. In Proceedings of International Conference on CAAD Future, Vol. 95 (pp. 749-759).

Goldschmidt, G. (1998). Creative architectural design: Reference versus precedence. J Archit Plan Res, 1998, 258-270.

Home Living (2023). Tips for Stylish Home Decor. https://www.homeliving.com

Houzz (2023). Interior Design Ideas. Retrieved from https://www.houzz.com

Jeong, H., & Lee, J. K. (2023). Study on the Applicability of Image Generation AI in Interior Architecture: Generating Images Based on Interior Design Styles. Proceeding of Spring Annual Conference of KHA, Vol. 35, No.1 (pp. 247-250), Jeju, Korea.

Jonson, B. (2005). Design ideation: the conceptual sketch in the digital age. Design studies, 26(6), 613-624. 10.1016/j.destud.2005.03.001

Karras, T., Laine, S., & Aila, T. (2019). A style-based generator architecture for generative adversarial networks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 4401-4410). 10.1109/CVPR.2019.00453

Kawar, B., Zada, S., Lang, O., Tov, O., Chang, H., Dekel, T., ... Irani, M. (2023). Imagic: Text-based real image editing with diffusion models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 6007-6017). 10.1109/CVPR52729.2023.00582

Kim, J., & Lee, J.K. (2020). Stochastic Detection of Interior Design Styles Using a Deep-Learning Model for Reference Images. Appl Sci, 10, 7299. 10.3390/app10207299

Kim, J., & Lee, J.-K. (2018). Auto-recognition of Interior Design Images for Managing Architectural Design References- Focused on the Module Implementation for Recognizing the Usage of Rooms of Korean Apartments. J Korean Inst Inter Des, 27, 13-20. 10.14774/JKIID.2018.27.5.013

Kim, K., Park, S., Lee, J., & Choo, J. (2023). Reference-based Image Composition with Sketch via Structure-aware Diffusion Model. arXiv preprint arXiv:2304.09748.

Lee, J. K., Lee, S., Kim, Y. C., Kim, S., & Hong, S. W. (2023). Augmented virtual reality and 360 spatial visualization for supporting user-engaged design. Journal of Computational Design and Engineering, 10(3), 1047-1059. 10.1093/jcde/qwad035

Lee, S. H, Kim, J. S., Song, J. Y., & Lee, J. K. (2020). Augmented Reality-Based Approach for Design On-Site Visualization - Focusing on the Example of Space Improvement Design at a University Academic Information Center. Journal of the Korean Society of Interior Design, 29(1), 97-104. 10.14774/JKIID.2020.29.1.097

Milgram, P., & Kishino, F. (1994). A taxonomy of mixed reality visual displays. IEICE TRANSACTIONS on Information and Systems, 77(12), 1321-1329.

OpenAI (2021). "ChatGPT: A Language Model by OpenAI". Retrieved from https://chat.openai.com/.

Oxman, R. (2006). Theory and design in the first digital age. Design studies, 27(3), 229-265. 10.1016/j.destud.2005.11.002

Phare, D. M., & Gu, N. (2018). Ostwald, M. Representation in Design Communication: Meaning-Making in a Collective Context. Front Built Environ, 4, 36. 10.3389/fbuil.2018.00036

Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., & Chen, M. (2022). Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125.

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 (pp. 8821-8831). PMLR.

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 (pp. 10684-10695). 10.1109/CVPR52688.2022.01042

Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., & Aberman, K. (2023). Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 22500-22510). 10.1109/CVPR52729.2023.02155

Shin, E., & Lee, J. K. (2022). Intelligent Reference Database Construction Based on 360 Panoramic Interior Space Photographs. Journal of the Korean Society of Spatial Design, 17(1), 477-485.

Stability AI (2022). "Stable Diffusion". Retrieved from https://stability.ai/blog/stable-diffusion-public-release

Yigitbas, E., Nowosad, A., & Engels, G. (2023). Supporting Construction and Architectural Visualization through BIM and AR/VR: A Systematic Literature Review. arXiv preprint arXiv:2306.12274. 10.1007/978-3-031-42283-6_8

Yoo, Y. J., & Lee, J. K. (2023). A Study on the Use of Image Generation AI Based on the Style of Famous Architects. Proceeding of Spring Annual Conference of KHA, Vol. 35, No. 1 (pp. 245-246), Jeju, Korea.

Information

Publisher :The Korean Housing Association
Publisher(Ko) :한국주거학회
Journal Title :Journal of the Korean Housing Association
Journal Title(Ko) :한국주거학회논문집
Volume : 34
No :6
Pages :017-024
Received Date : 2023-09-22
Revised Date : 2023-10-18
Accepted Date : 2023-10-23
DOI :https://doi.org/10.6107/JKHA.2023.34.6.017

Journal of the Korean Housing Association ISSN:2234-3571(Print) 2234-2257(Online) 한국주거학회논문집

All Issue