Convolution in the Cloud: Learning Deformable Kernels in 3D Graph Convolution Networks for Point Cloud Analysis

Zhi-Hao Lin, Sheng-Yu Huang, Yu-Chiang Frank Wang; The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 1800-1809

Abstract


Point clouds are among the popular geometry representations for 3D vision applications. However, without regular structures like 2D images, processing and summarizing information over these unordered data points are very challenging. Although a number of previous works attempt to analyze point clouds and achieve promising performances, their performances would degrade significantly when data variations like shift and scale changes are presented. In this paper, we propose 3D Graph Convolution Networks (3D-GCN), which is designed to extract local 3D features from point clouds across scales, while shift and scale-invariance properties are introduced. The novelty of our 3D-GCN lies in the definition of learnable kernels with a graph max-pooling mechanism. We show that 3D-GCN can be applied to 3D classification and segmentation tasks, with ablation studies and visualizations verifying the design of 3D-GCN.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Lin_2020_CVPR,
author = {Lin, Zhi-Hao and Huang, Sheng-Yu and Wang, Yu-Chiang Frank},
title = {Convolution in the Cloud: Learning Deformable Kernels in 3D Graph Convolution Networks for Point Cloud Analysis},
booktitle = {The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}