FloorGAN: Generative Network for Automated Floor Layout Generation

In this work, we propose a generative adversarial network, FloorGAN, to synthesize floor plans guided by user constraints. Our approach considers user inputs in the form of room types, and spatial relationships and generates layout designs that satisfy these requirements. We evaluate our approach on the dataset, RPLAN, consisting of 80,000 vector-graphics floor plans of residential buildings designed by professional architects. We perform both qualitative and quantitative analysis along three metrics - Realism, Diversity, and Compatibility to evaluate the generated layout designs. We compare our approach with the existing baselines and outperform on all these metrics. The layout designs generated by our approach are more realistic and of better quality.