Generating Topological Structure of Floorplans from Room Attributes
This addresses the need for topological information in indoor space analysis for applications like floorplan generation, though it appears incremental as it builds on prior iterative graph learning methods.
The paper tackles the problem of extracting topological information from room attributes for indoor space analysis by proposing Iterative and adaptive graph Topology Learning (ITL), which progressively predicts multiple relations between rooms to generate topological graph structures. Experiments on a new challenging indoor dataset demonstrate effectiveness in layout topology prediction and floorplan generation applications.
Analysis of indoor spaces requires topological information. In this paper, we propose to extract topological information from room attributes using what we call Iterative and adaptive graph Topology Learning (ITL). ITL progressively predicts multiple relations between rooms; at each iteration, it improves node embeddings, which in turn facilitates generation of a better topological graph structure. This notion of iterative improvement of node embeddings and topological graph structure is in the same spirit as \cite{chen2020iterative}. However, while \cite{chen2020iterative} computes the adjacency matrix based on node similarity, we learn the graph metric using a relational decoder to extract room correlations. Experiments using a new challenging indoor dataset validate our proposed method. Qualitative and quantitative evaluation for layout topology prediction and floorplan generation applications also demonstrate the effectiveness of ITL.