CT-block: a novel local and global features extractor for point cloud

11/30/2021
by   Shangwei Guo, et al.
1

Deep learning on the point cloud is increasingly developing. Grouping the point with its neighbors and conducting convolution-like operation on them can learn the local feature of the point cloud, but this method is weak to extract the long-distance global feature. Performing the attention-based transformer on the whole point cloud can effectively learn the global feature of it, but this method is hardly to extract the local detailed feature. In this paper, we propose a novel module that can simultaneously extract and fuse local and global features, which is named as CT-block. The CT-block is composed of two branches, where the letter C represents the convolution-branch and the letter T represents the transformer-branch. The convolution-branch performs convolution on the grouped neighbor points to extract the local feature. Meanwhile, the transformer-branch performs offset-attention process on the whole point cloud to extract the global feature. Through the bridge constructed by the feature transmission element in the CT-block, the local and global features guide each other during learning and are fused effectively. We apply the CT-block to construct point cloud classification and segmentation networks, and evaluate the performance of them by several public datasets. The experimental results show that, because the features learned by CT-block are much expressive, the performance of the networks constructed by the CT-block on the point cloud classification and segmentation tasks achieve state of the art.

READ FULL TEXT

page 6

page 7

page 9

research
05/24/2023

GTNet: Graph Transformer Network for 3D Point Cloud Classification and Semantic Segmentation

Recently, graph-based and Transformer-based deep learning networks have ...
research
05/04/2023

Point Transformer For Coronary Artery Labeling

Coronary CT angiography (CCTA) scans are widely used for diagnosis of co...
research
03/02/2022

3DCTN: 3D Convolution-Transformer Network for Point Cloud Classification

Although accurate and fast point cloud classification is a fundamental t...
research
09/23/2021

Fast Point Voxel Convolution Neural Network with Selective Feature Fusion for Point Cloud Semantic Segmentation

We present a novel lightweight convolutional neural network for point cl...
research
10/05/2022

Point Cloud Recognition with Position-to-Structure Attention Transformers

In this paper, we present Position-to-Structure Attention Transformers (...
research
04/23/2019

Lung Nodule Classification using Deep Local-Global Networks

Purpose: Lung nodules have very diverse shapes and sizes, which makes cl...
research
02/04/2022

Projection-based Point Convolution for Efficient Point Cloud Segmentation

Understanding point cloud has recently gained huge interests following t...

Please sign up or login with your details

Forgot password? Click here to reset