TY - JOUR
T1 - The role of latent representations for design space exploration of floorplans
AU - Azizi, Vahid
AU - Usman, Muhammad
AU - Sohn, Samuel S.
AU - Schwartz, Mathew
AU - Moon, Seonghyeon
AU - Faloutsos, Petros
AU - Kapadia, Mubbasir
N1 - Funding Information:
The author(s) disclosed receipt of the following financial support for the research, authorship, and/or publication of this article: This research has been partially funded by grants from ISSUM, and in part by NSF awards: (grant nos. IIS-1703883, IIS-1955404, and IIS-1955365).
Publisher Copyright:
© The Author(s) 2022.
PY - 2022
Y1 - 2022
N2 - Floorplans often require considering numerous factors, from the layout size to cost, numeric attributes such as room sizes, and other intrinsic properties such as connectivity between visible regions. Representing these complex factors is challenging, but doing so in a representative and efficient way can enable new modes of design exploration. Existing image and graph-based approaches of floorplans’ representation often failed to consider low-level space semantics, structural features, and space utilization with respect to its future inhabitants, which are all the critical elements to analyze design layouts. We present a latent-space representation of floorplans using gated recurrent unit variational autoencoder (GRU-VAE), where floorplans are represented as attributed graphs (encoded with the abovementioned features). Two local search approaches are presented to efficiently explore the latent space for optimizing and generating new floorplans for the given environment. Semantic, structural, and visibility metrics are evaluated individually and as a combined objective for optimizations.
AB - Floorplans often require considering numerous factors, from the layout size to cost, numeric attributes such as room sizes, and other intrinsic properties such as connectivity between visible regions. Representing these complex factors is challenging, but doing so in a representative and efficient way can enable new modes of design exploration. Existing image and graph-based approaches of floorplans’ representation often failed to consider low-level space semantics, structural features, and space utilization with respect to its future inhabitants, which are all the critical elements to analyze design layouts. We present a latent-space representation of floorplans using gated recurrent unit variational autoencoder (GRU-VAE), where floorplans are represented as attributed graphs (encoded with the abovementioned features). Two local search approaches are presented to efficiently explore the latent space for optimizing and generating new floorplans for the given environment. Semantic, structural, and visibility metrics are evaluated individually and as a combined objective for optimizations.
KW - Floorplan representation
KW - GRU variational autoencoder
KW - LSTM autoencoder
KW - attributed graphs
KW - floorplan generation
KW - floorplan optimization
KW - human behavioral features
KW - isovists
KW - latent search space
UR - http://www.scopus.com/inward/record.url?scp=85138407958&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85138407958&partnerID=8YFLogxK
U2 - 10.1177/00375497221115734
DO - 10.1177/00375497221115734
M3 - Article
AN - SCOPUS:85138407958
SN - 0037-5497
JO - SIMULATION
JF - SIMULATION
ER -