Graph-Based Generative Representation Learning of Semantically and Behaviorally Augmented Floorplans

TL;DR

This paper introduces a novel graph-based embedding and generative model for CAD floorplans that incorporates geometric, semantic, and behavioral data, enabling meaningful retrieval and generation of floorplan designs.

Contribution

It presents a new attributed graph embedding technique using an LSTM VAE that captures semantics and behavior, and demonstrates its effectiveness for retrieval and generation of floorplans.

Findings

The embedding produces meaningful and accurate representations.

The generative model can create new plausible floorplans.

User studies confirm the relevance of retrieved floorplans.

Abstract

Floorplans are commonly used to represent the layout of buildings. In computer aided-design (CAD) floorplans are usually represented in the form of hierarchical graph structures. Research works towards computational techniques that facilitate the design process, such as automated analysis and optimization, often use simple floorplan representations that ignore the semantics of the space and do not take into account usage related analytics. We present a floorplan embedding technique that uses an attributed graph to represent the geometric information as well as design semantics and behavioral features of the inhabitants as node and edge attributes. A Long Short-Term Memory (LSTM) Variational Autoencoder (VAE) architecture is proposed and trained to embed attributed graphs as vectors in a continuous space. A user study is conducted to evaluate the coupling of similar floorplans retrieved from the embedding space with respect to a given input (e.g., design layout). The qualitative, quantitative and user-study evaluations show that our embedding framework produces meaningful and accurate vector representations for floorplans. In addition, our proposed model is a generative model. We studied and showcased its effectiveness for generating new floorplans. We also release the dataset that we have constructed and which, for each floorplan, includes the design semantics attributes as well as simulation generated human behavioral features for further study in the community.