3D Model Generation on Architectural Plan and Section Training through Machine Learning

Machine learning, especially the GAN (Generative Adversarial Network) model, has been developed tremendously in recent years. Since the NVIDIA Machine Learning group presented the StyleGAN in December 2018, it has become a new way for designers to make machines learn different or similar types of architectural photos, drawings, and renderings, then generate (a) similar fake images, (b) style-mixing images, and (c) truncation trick images. The author both collected and created input image data, and specially made architectural plan and section drawing inputs with a clear design purpose, then applied StyleGAN to train specific networks on these datasets. With the training process, we could look into the deep relationship between these input architectural plans or sections, then generate serialized transformation images (truncation trick images) to form the 3D (three-dimensional) model with a decent resolution (up to 1024 × 1024 × 1024 pixels). Though the results of the 3D model generation are difficult to use directly in 3D spatial modeling, these unexpected 3D forms still could inspire new design methods and greater possibilities of architectural plan and section design.

[1]  Jonathon Shlens,et al.  Conditional Image Synthesis with Auxiliary Classifier GANs , 2016, ICML.

[2]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[3]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[4]  Timo Aila,et al.  A Style-Based Generator Architecture for Generative Adversarial Networks , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Hongjian Wang,et al.  3D Medical CT Images Reconstruction Based on VTK and Visual C++ , 2009, 2009 3rd International Conference on Bioinformatics and Biomedical Engineering.

[6]  THE CHURCH OF AI An examination of architecture in a posthuman design ecology , 2019 .

[7]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Pieter Abbeel,et al.  InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets , 2016, NIPS.

[9]  Simon Osindero,et al.  Conditional Generative Adversarial Nets , 2014, ArXiv.

[10]  Jaakko Lehtinen,et al.  Progressive Growing of GANs for Improved Quality, Stability, and Variation , 2017, ICLR.

[11]  Jeffrey Huang,et al.  Machinic Design Inference: from PokA©mon to Architecture - A Probabilistic Machine Learning Model for Generative Design using Game Levels Abstractions , 2019, Proceedings of the 24th Conference on Computer Aided Architectural Design Research in Asia (CAADRIA) [Volume 2].

[12]  R. Weron.  Electricity price forecasting: A review of the state-of-the-art with a look into the future , 2014 .

[13]  Marco Raberto,et al.  Modeling and forecasting of electricity spot-prices: Computational intelligence vs classical econometrics , 2014, AI Commun..

[14]  拓海 杉山,et al.  “Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告 , 2017 .

[15]  Kyle Steinfeld,et al.  Fresh Eyes: A Framework for the Application of Machine Learning to Generative Architectural Design, and a Report of Activities at Smartgeometry 2018 , 2019 .

[16]  Richard Laing,et al.  The impact of computer aided architectural design programs on conceptual design in an educational context , 2014 .

[17]  Leon A. Gatys,et al.  Image Style Transfer Using Convolutional Neural Networks , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Ben van Berkel,et al.  THE IMPACT OF COMPUTER AIDED ARCHITECTURAL DESIGN PROGRAMS ON CONCEPTUAL DESIGN IN AN EDUCATIONAL CONTEXT , 2014 .