Generative Architectural Design from Textual Prompts: Enhancing High-Rise Building Concepts for Assisting Architects
Source abstract
Abstract
In the early stages of architectural design, architects convert initial ideas into concrete design schemes, which heavily rely on their creativity and consume considerable time. Therefore, generative design methods based on artificial intelligence are promising for such tasks. However, effectively communicating design concepts to machines is challenging. To address this challenge, this paper proposes a novel cross-model approach for architectural design concepts using textual descriptions to assist architects, comprising a design concept extraction module and an architectural appearance generation module. The design concept extraction module adopts a contrastive learning framework to yield a text encoder with semantic extraction. Subsequently, the architectural appearance generation module proposes a novel deep sparse and text fusion generative adversarial network to convert the extracted design concept semantics into conceptual sketches, utilizing the unique sparsity of sketches. Additionally, it employs the pre-trained latent stable diffusion model to generate realistic and diverse high-rise building renderings, simulating the recreation processes of architects. The generated designs are evaluated qualitatively and quantitatively and further compared with existing real-life buildings to demonstrate the effectiveness of the proposed method. Furthermore, we demonstrate the feasibility of applying the proposed methodology in the early stages of architectural design by modeling a generated design.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Design Education and Practice · Architecture and Computational Design · BIM and Construction Integration
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Key Lab of Smart Prevention and Mitigation of Civil Engineering Disaster of the Ministry of Industry and Information Technology, Harbin 150090, China
School of Civil Engineering, Harbin Institute of Technology, Harbin 150090, China
Funding
National Key Research and Development Program of China · National Natural Science Foundation of China · China Postdoctoral Science Foundation
References (39)
Show source-provided references
1. How designers perceive sketches10.1016/j.destud.2006.02.001 ↗
2. Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N., and Weinberger, K.Q. (2014). Generative Adversarial Nets. Advances in Neural Information Processing Systems, Curran Associates, Inc.
3. The methodology for evaluating the fire resistance performance of concrete-filled steel tube columns by integrating conditional tabular generative adversarial networks and random oversampling10.1016/j.jobe.2024.110824 ↗
4. A fast-response-generation method for single-layer reticulated shells based on implicit parameter model of generative adversarial networks10.1016/j.jobe.2023.106563 ↗
5. Physical rule-guided generative adversarial network for automated structural layout design of steel frame-brace structures10.1016/j.jobe.2024.108943 ↗
6. Damage analysis and quantification of RC beams assisted by Damage-T Generative Adversarial Network10.1016/j.engappai.2022.105536 ↗
7. Nauata, N., Chang, K.-H., Cheng, C.-Y., Mori, G., and Furukawa, Y. (2020, January 23–28). House-Gan: Relational Generative Adversarial Networks for Graph-Constrained House layout Generation. Proceedings of the Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK. Proceedings, Part I 16.10.1007/978-3-030-58452-8_10 ↗
8. Nauata, N., Hosseini, S., Chang, K.-H., Chu, H., Cheng, C.-Y., and Furukawa, Y. (2021, January 19–25). House-gan++: Generative adversarial layout refinement network towards intelligent computational agent for professional architects. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Virtual.10.1109/CVPR46437.2021.01342 ↗
9. Chang, K.-H., Cheng, C.-Y., Luo, J., Murata, S., Nourbakhsh, M., and Tsuji, Y. (2021, January 11–17). Building-GAN: Graph-conditioned architectural volumetric design generation. Proceedings of the IEEE/CVF International Conference on Computer Vision, Virtual.10.1109/ICCV48922.2021.01174 ↗
10. Automated modular housing design using a module configuration algorithm and a coupled generative adversarial network (CoGAN)10.1016/j.autcon.2022.104234 ↗
11. Lee, D., Sugiyama, M., Luxburg, U., Guyon, I., and Garnett, R. (2016). Coupled Generative Adversarial Networks. Advances in Neural Information Processing Systems, Curran Associates, Inc.
12. Automated structural design of shear wall residential buildings using generative adversarial networks10.1016/j.autcon.2021.103931 ↗
13. Dual generative adversarial networks for automated component layout design of steel frame-brace structures10.1016/j.autcon.2022.104661 ↗
14. Automatic generation of architecture facade for historical urban renovation using generative adversarial network10.1016/j.buildenv.2022.108781 ↗
15. Zhu, J.-Y., Park, T., Isola, P., and Efros, A.A. (2017, January 22–29). Unpaired image-to-image translation using cycle-consistent adversarial networks. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.244 ↗
16. Qian, W., Xu, Y., Zuo, W., and Li, H. (2021). Self sparse generative adversarial networks. arXiv.10.26599/AIR.2022.9150005 ↗
17. A self-sparse generative adversarial network for autonomous early-stage design of architectural sketches10.1111/mice.12759 ↗
18. Artificial intelligence-designer for high-rise building sketches with user preferences10.1016/j.engstruct.2022.115171 ↗
19. Mirza, M., and Osindero, S. (2014). Conditional generative adversarial nets. arXiv.
20. Reed, S., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., and Lee, H. (2016, January 19–24). Generative adversarial text to image synthesis. Proceedings of the International Conference on Machine Learning, PMLR, New York, NY, USA.
21. Zhang, H., Xu, T., Li, H., Zhang, S., Wang, X., Huang, X., and Metaxas, D. (2017, January 22–29). Stackgan: Text to photo-realistic image synthesis with stacked generative adversarial networks. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.629 ↗
22. Stackgan++: Realistic image synthesis with stacked generative adversarial networks10.1109/TPAMI.2018.2856256 ↗
23. Qiao, T., Zhang, J., Xu, D., and Tao, D. (2019, January 16–20). Mirrorgan: Learning text-to-image generation by redescription. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00160 ↗
24. Tao, M., Tang, H., Wu, F., Jing, X.-Y., Bao, B.-K., and Xu, C. (2022, January 19–24). DF-GAN: A Simple and Effective Baseline for Text-to-Image Synthesis. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.10.1109/CVPR52688.2022.01602 ↗
25. Liao, W., Hu, K., Yang, M.Y., and Rosenhahn, B. (2022, January 18–24). Text to Image Generation with Semantic-Spatial Aware GAN. Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.10.1109/CVPR52688.2022.01765 ↗
26. DiverGAN: An Efficient and Effective Single-Stage Framework for Diverse Text-to-Image Generation10.1016/j.neucom.2021.12.005 ↗
27. Rombach, R., Blattmann, A., Lorenz, D., Esser, P., and Ommer, B. (2022, January 19–24). High-resolution image synthesis with latent diffusion models. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.10.1109/CVPR52688.2022.01042 ↗
28. Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., and Clark, J. (2021, January 18–24). Learning transferable visual models from natural language supervision. Proceedings of the 38th International Conference on Machine Learning, ICML 2021, Virtual.
29. Bidirectional recurrent neural networks10.1109/78.650093 ↗
30. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, Ł., and Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, Curran Associates, Inc.
31. He, K., Zhang, X., Ren, S., and Sun, J. (July, January 17). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.
32. Lim, J.H., and Ye, J.C. (2017). Geometric gan’. arXiv.
33. XDoG: An eXtended difference-of-Gaussians compendium including advanced image stylization10.1016/j.cag.2012.03.004 ↗
34. Loshchilov, I., and Hutter, F. (2017). Decoupled weight decay regularization. arXiv.
35. Loshchilov, I., and Hutter, F. (2016). Sgdr: Stochastic gradient descent with warm restarts. arXiv.
36. Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv.
37. Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., and Hochreiter, S. (2017). Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in Neural Information Processing Systems, Curran Associates, Inc.
38. Zhang, R., Isola, P., Efros, A.A., Shechtman, E., and Wang, O. (2018, January 18–22). The unreasonable effectiveness of deep features as a perceptual metric. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake, UT, USA.10.1109/CVPR.2018.00068 ↗
39. Participatory approach to draw ergonomic criteria for window design10.1016/j.ergon.2021.103098 ↗