Generative Adversarial Networks and Stylistic Plan Generation
Deep Neural Networks (DNNs) have emerged as a leading approach in ML for both discriminative and generative learning tasks. Deep discriminative models have demonstrated the ability to outperform human experts on classification and recognition tasks, while deep generative models have outperformed competing approaches in the synthesis of images. Generative Adversarial Networks (GANs) are a leading deep generative model that have demonstrated impressive results on 2D and 3D design tasks. Their exploration in the field of architecture, however, has been limited to the generation of generic architectural plans and facades.
This research addresses this gap in previous workand contributes knowledge on the application of GANs in the generation and analysis of architectural plans from specific stylistic movements in architecture.Specifically, a GAN is trained on a selection of residential plans by the architect Le Corbusier.The GAN is then used to synthesize new 2D plan images in the style of Corbusian planning.A series of experiments test different techniques architects might use when working with small datasets.They show that augmentation strategies can be effectively used with small training sets to improve image quality.
Figure 1 The diagram shows the generator and discriminator networks that comprise a GAN..
Figure 2 Part a-c show samples of GAN generated plans using the original 45 image Le Corbusier house dataset with no augmentation. Part d-f show samples generated with noise augmentation. Part g-i show samples generated using rotation. Part j-l show samples generated using noise and rotation as augmentation strategies.