| id |
ijac202220308 |
| authors |
Rodrigues, Ricardo C; Rovenir B Duarte |
| year |
2022 |
| title |
Generating floor plans with deep learning: A cross-validation assessment over different dataset sizes |
| source |
International Journal of Architectural Computing 2022, Vol. 20 - no. 3, pp. 630644 |
| summary |
The advent of deep learning has enabled a series of opportunities; one of them is the ability to tackle subjective factors on the floor plan design and make predictions though spatial semantic maps. Nonetheless, the amount available of data grows exponentially on a daily basis, in this sense, this research seeks to investigate deep generative methods of floor plan design and its relationship between data volume, with training time, quality and diversity in the outputs; in other words, what is the amount of data required to rapidly train models that return optimal results. In our research, we used a variation of the Conditional Generative Adversarial Network algorithm, that is, Pix2pix, and a dataset of approximately 80 thousand images to train 10 models and evaluate their performance through a series of computational metrics. The results show that the potential of this data-driven method depends not only on the diversity of the training set but also on the linearity of the distribution; therefore, high-dimensional datasets did not achieve good results. It is also concluded that models trained on small sets of data (800 images) may return excellent results if given the correct training instructions (Hyperparameters), but the best baseline to this generative task is in the mid-term, using around 20 to 30 thousand images with a linear distribution. Finally, it is presented standard guidelines for dataset design, and the impact of data curation along the entire process |
| keywords |
Dataset Reduction, Pix2pix, Artificial Intelligence, Deep Generative Models, GANs |
| series |
journal |
| references |
Content-type: text/plain
|
Alonso NM (2017)
 Suggestive Drawing Among Human and Artificial Intelligences
, Harvard GSD: Masters Dissertation
|
|
|
|
|
Bergmeir C and Ben΄itez JM (2012)
On the use of cross-validation for time series predictor evaluation
, Inf Sci (Ny) 2012; 191: 192213.
|
|
|
|
|
Buchanan R. (1992)
Wicked Problems in Design Thinking
, Des Issues 1992; 8: 5.
|
|
|
|
|
Chaillou S (2016)
ArchiGAN: Artificial Intelligence x Architecture
, Architectural Intelligence Singapore: Springer Singapore, pp 117127.
|
|
|
|
|
Chasalow K and Levy K (2021)
Representativeness in Statistics, Politics, and Machine Learning
, Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency. New York, NY, USA: ACM, pp 7789.
|
|
|
|
|
Chen Q, Wu Q, Tang R, et al (2003)
Intelligent Home 3D: Automatic 3D-House Design
, from Linguistic Descriptions Only,
|
|
|
|
|
Goodfellow I, Pouget-Abadie J, Mirza M, et al (2020)
Generative adversarial networks
, Commun ACM 2020; 63: 139144.
|
|
|
|
|
Hong T, Wang Z, Luo X, et al (2021)
State-of-the-art on research and applications of machine learning in the building life cycle
, Energy Build 2020; 212: 109831.
|
|
|
|
|
Hu R, Huang Z, Tang Y, et al (2020)
TAP-Net, Graph2Plan
, ACM Trans Graph 2020; 39: 114.
|
|
|
|
|
Huang W and Zheng H (2018)
Architectural drawings recognition and generation through machine learning
, Recalibration Imprecision Infidelity - Proc 38th Annu Conf Assoc Comput Aided Des Archit ACADIA, Mexico, 2018: 156165.
|
|
|
|
|
Isola P, Zhu JY, Zhou T, et al (2017)
Image-to-image translation with conditional adversarial networks
, Proc - 30th IEEE Conf Comput Vis Pattern Recognition CVPR 2017 2017, Honolulu, HI, 2017: 59675976.
|
|
|
|
|
Kalervo A, Ylioinas J, Haiki ¨ o M, et al (2016)
CubiCasa5K: A Dataset and an Improved Multi-task Model for Floorplan ¨ Image Analysis
, M Felsberg, P Forssen, I Sintorn, et al. ΄ Image Analysis, SCIA 2019. Cham: Springer, pp. 2840.
|
|
|
|
|
Larrain TV, Valencia A and Yuan PF (2017)
Spatial findings on Chilean architecture StyleGAN AI graphics
, Proceedings of the 26th International Conference ofthe Association for Computer-Aided Architectural Design Research in Asia (CAADRIA), Hong Kong: Association for Computer-Aided Architectural Design Research in Asia (CAADRIA), 2021, pp 251260.
|
|
|
|
|
Leach N (2020)
Architecture in the Age of Artificial Intelligence: An Introduction to AI for Architects
, 1st ed London: Bloomsbury Visual Arts, 2022.
|
|
|
|
|
LIFULL CL (2002)
LIFULL HOMES High Resolution Floor Plan Image Data
, Informatics Research Data Repository 2016, DOI: 10.32130/idr.6.2.
|
|
|
|
|
Lobos D and Donath D (2011)
The problem of space layout in architecture: A survey and reflections
, Arquitetura Rev 2010; 6: 136161.
|
|
|
|
|
Mahankali R, Johnson BR and Anderson AT (2018)
Deep learning in design workflows: The elusive design pixel
, Int J Archit Comput 2018; 16: 328340.
|
|
|
|
|
Newton D. (2021)
Generative Deep Learning in Architectural Design
, Technol Archit Des 2019; 3: 176189.
|
|
|
|
|
Nuha FU and Afiahayati A (2018)
Training dataset reduction on generative adversarial network
, Procedia Comput Sci 2018; 144: 133139.
|
|
|
|
|
Parmar G, Zhang R and Zhu J-Y (2022)
On Aliased Resizing and Surprising Subtleties in GAN Evaluation
, CVPR, 2022. arXiv.
|
|
|
|
| last changed |
2024/04/17 14:30 |
|
