House-GAN++: Generative Adversarial Layout Refinement Networks
Abstract
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.
Cite
@article{arxiv.2103.02574,
title = {House-GAN++: Generative Adversarial Layout Refinement Networks},
author = {Nelson Nauata and Sepidehsadat Hosseini and Kai-Hung Chang and Hang Chu and Chin-Yi Cheng and Yasutaka Furukawa},
journal= {arXiv preprint arXiv:2103.02574},
year = {2021}
}