Cross self-attention network for 3D point cloud

It is a challenge to design a deep neural network for raw point cloud, which is disordered and unstructured data. In this paper, we introduce a cross self-attention network (CSANet) to solve raw point cloud classification and segmentation tasks. It has permutation invariance and can learn the coordi...

Full description

Saved in:
Bibliographic Details
Published inKnowledge-based systems Vol. 247; p. 108769
Main Authors Wang, Gaihua, Zhai, Qianyu, Liu, Hong
Format Journal Article
LanguageEnglish
Published Amsterdam Elsevier B.V 08.07.2022
Elsevier Science Ltd
Subjects
Artificial neural networks
Classification
Cloud computing
Deep learning
Image segmentation
Multi-scale fusion
Permutations
Point cloud
Self-attention
Semantic segmentation
Shape classification
Three dimensional models
Unstructured data
Deep learning
Shape classification
Point cloud
Multi-scale fusion
Semantic segmentation
Self-attention
Online AccessGet full text

Cover

More Information
Summary:It is a challenge to design a deep neural network for raw point cloud, which is disordered and unstructured data. In this paper, we introduce a cross self-attention network (CSANet) to solve raw point cloud classification and segmentation tasks. It has permutation invariance and can learn the coordinates and features of point cloud at the same time. To better capture features of different scales, a multi-scale fusion (MF) module is proposed, which can adaptively consider the information of different scales and establish a fast descent branch to bring richer gradient information. Extensive experiments on ModelNet40, ShapeNetPart, and S3DIS demonstrate that the proposed method can achieve competitive results.
ISSN:0950-7051
1872-7409
DOI:10.1016/j.knosys.2022.108769