LayoutEnhancer: Generating Good Indoor Layouts from Imperfect Data
Document Type
Conference Proceeding
Publication Date
11-29-2022
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.
Identifier
85143980916 (Scopus)
ISBN
[9781450394703]
Publication Title
Proceedings SIGGRAPH Asia 2022 Conference Papers
External Full Text Location
https://doi.org/10.1145/3550469.3555425
Grant
P 29981
Fund Ref
Austrian Science Fund
Recommended Citation
Leimer, Kurt; Guerrero, Paul; Weiss, Tomer; and Musialski, Przemyslaw, "LayoutEnhancer: Generating Good Indoor Layouts from Imperfect Data" (2022). Faculty Publications. 2494.
https://digitalcommons.njit.edu/fac_pubs/2494
