Efficient retrieval of 3D building models using embeddings of attributed subgraphs

Abstract

We present a novel method for retrieval and classification of 3D building models that is tailored to the specific requirements of architects. In contrast to common approaches our algorithm relies on the interior spatial arrangement of rooms instead of exterior geometric shape. We first represent the internal topological building structure by a Room Connectivity Graph (RCG). Each room is characterized by a node. Connections between rooms like e.g. doors are represented by edges. Nodes and edges are additionally assigned attributes reflecting room and edge properties like e.g area or window size. To enable fast and efficient retrieval and classification with RCGs, we transform the structured graph representation into a vector-based one. We first decompose the RCG into a set of subgraphs. For each subgraph, we compute the similarity to a set of codebook graphs. Aggregating all similarity values finally provides us with a single vector for each RCG which enables fast retrieval and classification. For evaluation, we introduce a classification scheme that was carefully developed following common guidelines in architecture.We finally provide comprehensive experiments showing that the introduced subgraph embeddings yield superior performance compared to state-of-the-art graph retrieval approaches.

Efficient Top-k Graph Similarity Search With GED Constraints

“…1 We first pop the head element c from C. Then, we look up the head c of C and set a target lower bound to lb(q, c ) + 1, where lb(q, c ) is the current lower bound of c . 2 We incrementally tighten the lower bound of c up to the target. 3 If we successfully tighten the lower bound of c, we push c into C. We can fail to tighten the lower bound of c if and only if we obtain ged(q, c) which is less than the target (see Algorithm 3).…”

A Survey on Applications of Bipartite Graph Edit Distance

“…Image Analysis [19][20][21][22][23][24] Handwritten Document Analysis [25][26][27][28][29][30][31][32][33] Biometrics [34][35][36][37][38][39][40] Bio-and Chemoinformatics [41][42][43][44][45][46] Knowledge and Process Management [47][48][49][50] Malware Detection [51][52][53][54] Other Applications [55][56][57][58] Fig. 1: Taxonomy of the reviewed application fields and papers that use the framework for Bipartite Graph Edit Distance (BP).…”

“…Graphs are also used for 3D-images analysis. In [24], for instance, graphs are used to represent topological building structures by a so called Room Connectivity Graph. To this end, nodes represent rooms and are labelled by three-dimensional characteristics of the room.…”