Generative Adversarial Networks - Facade 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. This research explores the use of GANs to synthesize stylized facades from small training sets
Figure 1 Examples of Gothic facades generated with DCGAN after 500 epochs.
Figure 2Examples of facades generated with DCGAN from the CMP facades dataset after 500 epochs.