RIConv++: Effective rotation invariant convolutions for 3D point clouds deep learning
3D point clouds deep learning is a promising field of research that allows a neural network to learn features of point clouds directly, making it a robust tool for solving 3D scene understanding tasks. While recent works show that point cloud convolutions can be invariant to translation and point pe...
Saved in:
Main Authors: | , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2022
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/7933 https://ink.library.smu.edu.sg/context/sis_research/article/8936/viewcontent/2202.13094.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.sis_research-8936 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-89362023-07-14T07:02:17Z RIConv++: Effective rotation invariant convolutions for 3D point clouds deep learning ZHANG, Zhiyuan HUA, Binh-Son YEUNG, Sai-Kit 3D point clouds deep learning is a promising field of research that allows a neural network to learn features of point clouds directly, making it a robust tool for solving 3D scene understanding tasks. While recent works show that point cloud convolutions can be invariant to translation and point permutation, investigations of the rotation invariance property for point cloud convolution has been so far scarce. Some existing methods perform point cloud convolutions with rotation-invariant features, existing methods generally do not perform as well as translation-invariant only counterpart. In this work, we argue 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 simple yet effective convolution operator that enhances feature distinction by designing powerful rotation invariant features from the local regions. We consider the relationship between the point of interest and its neighbors as well as the internal relationship of the neighbors to largely improve the feature descriptiveness. Our network architecture can capture both local and global context by simply tuning the neighborhood size in each convolution layer. We conduct several experiments on synthetic and real-world point cloud classifications, part segmentation, and shape retrieval to evaluate our method, which achieves the state-of-the-art accuracy under challenging rotations. 2022-03-01T08:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/7933 info:doi/10.1007/s11263-022-01601-z https://ink.library.smu.edu.sg/context/sis_research/article/8936/viewcontent/2202.13094.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University 3D Point Cloud Convolutional Neural Networks Deep Learning Rotation Invariance Artificial Intelligence and Robotics Software Engineering |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
3D Point Cloud Convolutional Neural Networks Deep Learning Rotation Invariance Artificial Intelligence and Robotics Software Engineering |
spellingShingle |
3D Point Cloud Convolutional Neural Networks Deep Learning Rotation Invariance Artificial Intelligence and Robotics Software Engineering ZHANG, Zhiyuan HUA, Binh-Son YEUNG, Sai-Kit RIConv++: Effective rotation invariant convolutions for 3D point clouds deep learning |
description |
3D point clouds deep learning is a promising field of research that allows a neural network to learn features of point clouds directly, making it a robust tool for solving 3D scene understanding tasks. While recent works show that point cloud convolutions can be invariant to translation and point permutation, investigations of the rotation invariance property for point cloud convolution has been so far scarce. Some existing methods perform point cloud convolutions with rotation-invariant features, existing methods generally do not perform as well as translation-invariant only counterpart. In this work, we argue 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 simple yet effective convolution operator that enhances feature distinction by designing powerful rotation invariant features from the local regions. We consider the relationship between the point of interest and its neighbors as well as the internal relationship of the neighbors to largely improve the feature descriptiveness. Our network architecture can capture both local and global context by simply tuning the neighborhood size in each convolution layer. We conduct several experiments on synthetic and real-world point cloud classifications, part segmentation, and shape retrieval to evaluate our method, which achieves the state-of-the-art accuracy under challenging rotations. |
format |
text |
author |
ZHANG, Zhiyuan HUA, Binh-Son YEUNG, Sai-Kit |
author_facet |
ZHANG, Zhiyuan HUA, Binh-Son YEUNG, Sai-Kit |
author_sort |
ZHANG, Zhiyuan |
title |
RIConv++: Effective rotation invariant convolutions for 3D point clouds deep learning |
title_short |
RIConv++: Effective rotation invariant convolutions for 3D point clouds deep learning |
title_full |
RIConv++: Effective rotation invariant convolutions for 3D point clouds deep learning |
title_fullStr |
RIConv++: Effective rotation invariant convolutions for 3D point clouds deep learning |
title_full_unstemmed |
RIConv++: Effective rotation invariant convolutions for 3D point clouds deep learning |
title_sort |
riconv++: effective rotation invariant convolutions for 3d point clouds deep learning |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2022 |
url |
https://ink.library.smu.edu.sg/sis_research/7933 https://ink.library.smu.edu.sg/context/sis_research/article/8936/viewcontent/2202.13094.pdf |
_version_ |
1772829242206191616 |