ShellNet: Efficient Point Cloud Convolutional Neural Networks Using Concentric Shells Statistics

By Zhiyuan Zhang, Binh-Son Hua, Sai-Kit Yeung. IEEE International Conference on Computer Vision, 2019

407 citations recorded by the source corpus.

Deep learning with 3D data has progressed significantly since the introduction of convolutional neural networks that can handle point order ambiguity in point cloud data. While being able to achieve good accuracies in various scene understanding tasks, previous methods often have low training speed and complex network architecture. In this paper, we address these problems by proposing an efficient end-to-end permutation invariant convolution for point cloud deep learning. Our simple yet effective convolution operator named ShellConv uses statistics from concentric spherical shells to define representative features and resolve the point order ambiguity, allowing traditional convolution to perform on such features. Based on ShellConv we further build an efficient neural network named ShellNet to directly consume the point clouds with larger receptive fields while maintaining less layers. We demonstrate the efficacy of ShellNet by producing state-of-the-art results on object classification, object part segmentation, and semantic scene segmentation while keeping the network very fast to train.

Subfields: Computational Mechanics, Environmental Engineering, Geology

View Paper: https://www.semanticscholar.org/paper/b39342d0171678041f5259b7ca400d72d2445f2d

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

1. Or Litany
2. Charles Ruizhongtai Qi
3. Binh-Son Hua
4. Sai-Kit Yeung
5. Leonidas J. Guibas
6. Cheng Wang
7. Saifullahi Aminu Bello
8. Shangshu Yu

In Environmental Engineering

1. Cheng Wang
2. Saifullahi Aminu Bello
3. Shangshu Yu
4. Sai-Kit Yeung
5. Binh-Son Hua
6. Charles Ruizhongtai Qi
7. Mohammed Bennamoun
8. Hao Liu

In Geology

1. Or Litany
2. Charles Ruizhongtai Qi
3. Leonidas J. Guibas
4. Binh-Son Hua
5. Sai-Kit Yeung
6. Saining Xie
7. Qingyong Hu
8. Cheng Wang

Citations in the corpus

• RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds (2019, background): “For fair comparison, we only include the results of recently published strong baselines [4, 52, 53, 46, 69, 56, 26] and the current state-of-the-art approach KPConv [54].”
• PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding (2020, background): “Second, is the choice of neighborhood aggregation mechanism which could either be hierarchical [48, 33, 82, 16, 35], spatial CNN-like [30, 73, 37, 85, 59], spectral [78, 62, 65] or graph-based [72, 64, 68, 54].”
• Review: deep learning on 3D point clouds (2020, background): “ShellNet [46] Random Sampling Spherical Shells 1D convolution”
• Rotation Invariant Convolutions for 3D Point Clouds Deep Learning (2019, background): “Such process has been shown to be highly efficient for local feature learning [44].”
• Deep Learning for 3D Point Clouds: A Survey (2019, background): “Although several approaches [42], [170], [182] have achieved a remarkable overall performance, their performance on minority classes is still limited.”