House-GAN++: Generative Adversarial Layout Refinement Networks

TL;DR

This paper introduces House-GAN++, a novel generative adversarial network for automated floorplan refinement that iteratively improves layouts using a graph-constrained relational and conditional GAN architecture, achieving state-of-the-art results.

Contribution

The paper presents a new GAN architecture combining relational and conditional components for iterative floorplan refinement, with a simple training process that outperforms existing methods.

Findings

Significant improvements over current state-of-the-art methods.

Competitive results against professional architect-designed floorplans.

Effective non-iterative training process for layout generation.

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.