SPNet: Deep 3D Object Classification and Retrieval using Stereographic Projection

By Mohsen Yavartanoo, Euyoung Kim, Kyoung Mu Lee. 2018

80 citations recorded by the source corpus.

We propose an efficient Stereographic Projection Neural Network (SPNet) for learning representations of 3D objects. We first transform a 3D input volume into a 2D planar image using stereographic projection. We then present a shallow 2D convolutional neural network (CNN) to estimate the object category followed by view ensemble, which combines the responses from multiple views of the object to further enhance the predictions. Specifically, the proposed approach consists of four stages: (1) Stereographic projection of a 3D object, (2) view-specific feature learning, (3) view selection and (4) view ensemble. The proposed approach performs comparably to the state-of-the-art methods while having substantially lower GPU memory as well as network parameters. Despite its lightness, the experiments on 3D object classification and shape retrievals demonstrate the high performance of the proposed method.

Subfields: Computational Mechanics, Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Computer Graphics and Computer-Aided Design

In Computer Vision and Pattern Recognition

Citations in the corpus

Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data (2019, background): “Early attempts to classifying point clouds were developed by adapting ideas from deep learning on images, e.g ., using multiple view images [39, 48, 46, 22], or applying convolutions on 3D voxel grids [27, 43].”
View-GCN: View-Based Graph Convolutional Network for 3D Shape Analysis (2020, methodology): “View-based methods [8, 15, 20, 27, 28, 41, 47, 50, 54] are based on aggregation of multi-view features for recognizing shape categories based on multi-view 2D images.”