House-GAN++: Generative Adversarial Layout Refinement Networks
This work addresses the problem of automated floorplan generation for architects and designers, offering an incremental advancement through iterative refinement and meta-optimization techniques.
The paper tackles automated floorplan generation by proposing a generative adversarial layout refinement network that integrates graph-constrained relational GAN and conditional GAN for iterative refinement, achieving significant improvements over state-of-the-art methods and even competing with ground-truth designs by professional architects.
This paper proposes a novel generative adversarial layout refinement network for automated floorplan generation. Our architecture is an integration of a graph-constrained relational GAN and a conditional GAN, where a previously generated layout becomes the next input constraint, enabling iterative refinement. A surprising discovery of our research is that a simple non-iterative training process, dubbed component-wise GT-conditioning, is effective in learning such a generator. The iterative generator also creates a new opportunity in further improving a metric of choice via meta-optimization techniques by controlling when to pass which input constraints during iterative layout refinement. Our qualitative and quantitative evaluation based on the three standard metrics demonstrate that the proposed system makes significant improvements over the current state-of-the-art, even competitive against the ground-truth floorplans, designed by professional architects.