3D model retrieval and classification by semi-supervised learning with content-based similarity

Graph-based characteristic view set extraction and matching for 3D model retrieval

“…In this section, we will review the representative work in the field of 3D model retrieval [36,39,8,55]. 3D model retrieval methods are mainly classified into two categories [19,22]: (1) geometry-based techniques [50,42,26,34,10], (2) view-based techniques [9,54,59].…”

A Novel 3D CAD Model Retrieval Method Based on Vertices Classification and Weights Combination Optimization

“…In [26], 3D models are represented as probability distributions of binary variables on a 3D voxel grid and the proposed method uses a Convolutional Deep Belief Network to learn the distribution of complex 3D shapes across different categories and arbitrary poses from raw CAD data. In [27], the distance between 3D models is computed based on distance histogram features and 3D moment features. Using this distance measure, the relationships between all 3D models in dataset are formulated as a graph structure.…”

Indoor scene understanding via monocular RGB-D images

“…This makes segmentation and recognition difficult in situations with complex textures, serious occlusions or the diversity of same thing from different viewpoints. As a consequence of this, 3D data are now considered as significant in many works [11,12,27], and researchers have started to seek 3D information from 2D data. It is not always convenient to obtain 3D data directly, and numerous 3D estimating procedures have been proposed.…”