Multi-Modal Clique-Graph Matching for View-Based 3D Model Retrieval

Abstract

Multi-view matching is an important but a challenging task in view-based 3D model retrieval. To address this challenge, we propose an original multi-modal clique graph (MCG) matching method in this paper. We systematically present a method for MCG generation that is composed of cliques, which consist of neighbor nodes in multi-modal feature space and hyper-edges that link pairwise cliques. Moreover, we propose an image set-based clique/edgewise similarity measure to address the issue of the set-to-set distance measure, which is the core problem in MCG matching. The proposed MCG provides the following benefits: 1) preserves the local and global attributes of a graph with the designed structure; 2) eliminates redundant and noisy information by strengthening inliers while suppressing outliers; and 3) avoids the difficulty of defining high-order attributes and solving hyper-graph matching. We validate the MCG-based 3D model retrieval using three popular single-modal data sets and one novel multi-modal data set. Extensive experiments show the superiority of the proposed method through comparisons. Moreover, we contribute a novel real-world 3D object data set, the multi-view RGB-D object data set. To the best of our knowledge, it is the largest real-world 3D object data set containing multi-modal and multi-view information.

Multiple Discrimination and Pairwise CNN for view-based 3D object retrieval

“…Since different evaluation criterions are employed in different datasets, thus, for a fair comparison, different evaluation criterions are also utilized according to related works ( [39], [6], [38], [30]). Concretely, in EHT, NTU60 and MVRED datasets, seven evaluation criterions are utilized to assess its performance, and they are Nearest Neighbor (NN), First Tier (FT), Second Tier (ST), F-measure (F), Discounted Cumulative Gain (DCG) ( [41]), Average Normalized Modified Retrieval Rank (ANMRR) and Precision-Recall Curve (PR-Curve).…”

Learning Discriminative 3D Shape Representations by View Discerning Networks

“…They constructed a view-graph model with spatial information of different views, thus transforming the issue of shape distance measurement into a graph matching problem. They [12] also designed the multi-modal clique graph, which utilizes hyper-edges and edges to respectively link pairwise shape cliques and views within a clique. Such a graph design could strengthen inliers while suppressing outliers.…”

“…3D model-based methods like [2], [3], [4], [5], [6], [7], [8] extract high-level descriptors directly from the raw representation of 3D shapes. By contrast, view-based methods like [11], [12], [13], [14], [15] aim to extract features from 2D images of a 3D shape. The final shape descriptor is constructed from these view features.…”

Adaptive Collaborative Similarity Learning for Unsupervised Multi-view Feature Selection

“…With the advent of big data, multi-view features with high dimensions are widely employed to represent the complex data in various research fields, such as multimedia computing, machine learning and data mining [Liu et al, 2016;Zhu et al, 2017b;Zhu et al, 2015;. On the one * Corresponding Author hand, with multi-view features, the data could be characterized more precisely and comprehensively from different perspectives.…”