TY - GEN
T1 - LayoutEnhancer
T2 - SIGGRAPH Asia 2022 - Computer Graphics and Interactive Techniques Conference - Asia, SA 2022
AU - Leimer, Kurt
AU - Guerrero, Paul
AU - Weiss, Tomer
AU - Musialski, Przemyslaw
N1 - Publisher Copyright:
© 2022 Owner/Author.
PY - 2022/11/29
Y1 - 2022/11/29
N2 - 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.
AB - 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.
KW - indoor layout synthesis
KW - interior design
KW - neural networks
UR - http://www.scopus.com/inward/record.url?scp=85143980916&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85143980916&partnerID=8YFLogxK
U2 - 10.1145/3550469.3555425
DO - 10.1145/3550469.3555425
M3 - Conference contribution
AN - SCOPUS:85143980916
T3 - Proceedings - SIGGRAPH Asia 2022 Conference Papers
BT - Proceedings - SIGGRAPH Asia 2022 Conference Papers
A2 - Spencer, Stephen N.
PB - Association for Computing Machinery, Inc
Y2 - 6 December 2022 through 9 December 2022
ER -