LayoutEnhancer: Generating Good Indoor Layouts from Imperfect Data

TL;DR

LayoutEnhancer introduces a novel method combining expert knowledge with Transformer-based generative models to produce high-quality indoor layouts, even from imperfect or limited datasets, aiding designers and amateurs.

Contribution

The paper presents a new approach that integrates differentiable expert knowledge into data-driven layout synthesis, addressing data limitations and enhancing layout quality.

Findings

Effective biasing of layouts with expert knowledge

Improved layout quality from imperfect datasets

Assists both professional designers and amateurs

Abstract

We address the problem of indoor layout synthesis, which is a topic of continuing research interest in computer graphics. The newest works made significant progress using data-driven generative methods; however, these approaches rely on suitable datasets. In practice, desirable layout properties may not exist in a dataset, for instance, specific expert knowledge can be missing in the data. We propose a method that combines expert knowledge, for example, knowledge about ergonomics, with a data-driven generator based on the popular Transformer architecture. The knowledge is given as differentiable scalar functions, which can be used both as weights or as additional terms in the loss function. Using this knowledge, the synthesized layouts can be biased to exhibit desirable properties, even if these properties are not present in the dataset. Our approach can also alleviate problems of lack of data and imperfections in the data. Our work aims to improve generative machine learning for modeling and provide novel tools for designers and amateurs for the problem of interior layout creation.