House-GAN++: Generative Adversarial Layout Refinement Network towards Intelligent Computational Agent for Professional Architects

Figure 1 . The paper makes a breakthrough in automated house layout generation. The right is the mix of a ground-truth design by an architect and our generated samples, based on the input bubble-diagram. (The second from the right is the ground-truth.) A novel generative adversarial layout refinement network is trained to repeatedly apply and refine the design towards perfection.