Adversarial Model for Rotated Indoor Scenes Planning

TL;DR

This paper introduces an adversarial model that improves furniture layout generation for rotated interior scenes, effectively handling rotation and reducing mode collapse, validated on a large real-world dataset.

Contribution

The paper presents a novel adversarial model with specialized modules for interior scene synthesis under rotation, enhancing layout quality and diversity.

Findings

Higher-quality layouts for multiple room types

Effective handling of interior rotation in scene synthesis

Reduced mode collapse during layout generation

Abstract

In this paper, we propose an adversarial model for producing furniture layout for interior scene synthesis when the interior room is rotated. The proposed model combines a conditional adversarial network, a rotation module, a mode module, and a rotation discriminator module. As compared with the prior work on scene synthesis, our proposed three modules enhance the ability of auto-layout generation and reduce the mode collapse during the rotation of the interior room. We conduct our experiments on a proposed real-world interior layout dataset that contains 14400 designs from the professional designers. Our numerical results demonstrate that the proposed model yields higher-quality layouts for four types of rooms, including the bedroom, the bathroom, the study room, and the tatami room.