Global Context Aware Convolutions for 3D Point Cloud Understanding

08/07/2020
by   Zhiyuan Zhang, et al.
1

Recent advances in deep learning for 3D point clouds have shown great promises in scene understanding tasks thanks to the introduction of convolution operators to consume 3D point clouds directly in a neural network. Point cloud data, however, could have arbitrary rotations, especially those acquired from 3D scanning. Recent works show that it is possible to design point cloud convolutions with rotation invariance property, but such methods generally do not perform as well as translation-invariant only convolution. We found that a key reason is that compared to point coordinates, rotation-invariant features consumed by point cloud convolution are not as distinctive. To address this problem, we propose a novel convolution operator that enhances feature distinction by integrating global context information from the input point cloud to the convolution. To this end, a globally weighted local reference frame is constructed in each point neighborhood in which the local point set is decomposed into bins. Anchor points are generated in each bin to represent global shape features. A convolution can then be performed to transform the points and anchor features into final rotation-invariant features. We conduct several experiments on point cloud classification, part segmentation, shape retrieval, and normals estimation to evaluate our convolution, which achieves state-of-the-art accuracy under challenging rotations.

READ FULL TEXT
research
02/26/2022

RIConv++: Effective Rotation Invariant Convolutions for 3D Point Clouds Deep Learning

3D point clouds deep learning is a promising field of research that allo...
research
08/17/2019

Rotation Invariant Convolutions for 3D Point Clouds Deep Learning

Recent progresses in 3D deep learning has shown that it is possible to d...
research
08/13/2019

Interpolated Convolutional Networks for 3D Point Cloud Understanding

Point cloud is an important type of 3D representation. However, directly...
research
09/23/2021

SPNet: Multi-Shell Kernel Convolution for Point Cloud Semantic Segmentation

Feature encoding is essential for point cloud analysis. In this paper, w...
research
12/15/2018

3DTI-Net: Learn Inner Transform Invariant 3D Geometry Features using Dynamic GCN

Deep learning on point clouds has made a lot of progress recently. Many ...
research
09/07/2020

DV-ConvNet: Fully Convolutional Deep Learning on Point Clouds with Dynamic Voxelization and 3D Group Convolution

3D point cloud interpretation is a challenging task due to the randomnes...
research
09/15/2020

A Self Contour-based Rotation and Translation-Invariant Transformation for Point Clouds Recognition

Recently, several direct processing point cloud models have achieved sta...

Please sign up or login with your details

Forgot password? Click here to reset