View-Based 3D Model Retrieval via Multi-graph Matching

Weizhi Nie, Anan Liu, Yahui Hao, Yuting Su

Abstract: With the rapid development of 3D technology, 3D model retrieval has attracted a large amount of interest in computer vision field. In this paper, we propose a composition-based multi-graph matching method in this paper. Firstly, compute the pairwise matching affinity one-to-one graph matching. Secondly, seek the optimal intermediate graph by diverse graph matching orders, according to the consistency of global matching. Finally, the classic optimization method is used to get the best matching result for similarity measurement. We validate our approach using ETH, NTU and MV-RED 3D model datasets with convolutional neural network features. Extensive experiments show the superiority of the proposed method.

External IDs:dblp:journals/npl/NieLHS18