Relation-Shape Convolutional Neural Network for Point Cloud Analysis

Published in

Computer Vision and Pattern Recognition(2019)

External Links:

Generate Graph DownloadPDF

TL;DR

RS-CNN, namely, Relation-Shape Convolutional Neural Network, which extends regular grid CNN to irregular configuration for point cloud analysis, achieves the state of the arts and a hierarchical architecture can be developed to achieve contextual shape-aware learning for Point cloud analysis.

Abstract

Point cloud analysis is very challenging, as the shape implied in irregular points is difficult to capture. In this paper, we propose RS-CNN, namely, Relation-Shape Convolutional Neural Network, which extends regular grid CNN to irregular configuration for point cloud analysis. The key to RS-CNN is learning from relation, i.e., the geometric topology constraint among points. Specifically, the convolutional weight for local point set is forced to learn a high-level relation expression from predefined geometric priors, between a sampled point from this point set and the others. In this way, an inductive local representation with explicit reasoning about the spatial layout of points can be obtained, which leads to much shape awareness and robustness. With this convolution as a basic operator, RS-CNN, a hierarchical architecture can be developed to achieve contextual shape-aware learning for point cloud analysis. Extensive experiments on challenging benchmarks across three tasks verify RS-CNN achieves the state of the arts.

Authors

Yongcheng Liu

1 papers

Bin Fan

2 papers

Shiming Xiang

2 papers

References51 items

SeqViews2SeqLabels: Learning 3D Global Features via Aggregating Sequential Views by RNN With Attention

Multiresolution Tree Networks for 3D Point Cloud Processing

PointSIFT: A SIFT-like Network Module for 3D Point Cloud Semantic Segmentation

RGCNN: Regularized Graph CNN for Point Cloud Segmentation

Attentional ShapeContextNet for Point Cloud Recognition

Relation-Shape Convolutional Neural Network for Point Cloud Analysis

Published in

Computer Vision and Pattern Recognition(2019)

External Links:

Generate Graph DownloadPDF

TL;DR

Abstract

Authors

Yongcheng Liu

1 papers

Bin Fan

2 papers

Shiming Xiang

2 papers

References51 items

SeqViews2SeqLabels: Learning 3D Global Features via Aggregating Sequential Views by RNN With Attention

Multiresolution Tree Networks for 3D Point Cloud Processing

PointSIFT: A SIFT-like Network Module for 3D Point Cloud Semantic Segmentation

RGCNN: Regularized Graph CNN for Point Cloud Segmentation

Attentional ShapeContextNet for Point Cloud Recognition

Chunhong Pan

2 papers

GVCNN: Group-View Convolutional Neural Networks for 3D Shape Recognition

Deep Parametric Continuous Convolutional Neural Networks

SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters

Point convolutional neural networks by extension operators

Local Spectral Graph Convolution for Point Set Feature Learning

SO-Net: Self-Organizing Network for Point Cloud Analysis

Flex-Convolution - Million-Scale Point-Cloud Learning Beyond Grid-Worlds

SPLATNet: Sparse Lattice Networks for Point Cloud Processing

Recurrent Slice Networks for 3D Segmentation of Point Clouds

Dynamic Graph CNN for Learning on Point Clouds

PointCNN: Convolution On X-Transformed Points

Adaptive Graph Convolutional Neural Networks

Mining Point Cloud Local Structures by Kernel Correlation and Graph Pooling

Pointwise Convolutional Neural Networks

Relation Networks for Object Detection

Non-local Neural Networks

PCPNet Learning Local Shape Properties from Raw Point Clouds

Generalized Convolutional Neural Networks for Point Cloud Data

DeepShape: Deep-Learned Shape Descriptor for 3D Shape Retrieval

PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space

Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs

Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Models

Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputs

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentation

Multi-View 3D Object Retrieval With Deep Embedding Network

OctNet: Learning Deep 3D Representations at High Resolutions

A scalable active framework for region annotation in 3D shape collections

Dynamic Filter Networks

Volumetric and Multi-view CNNs for Object Classification on 3D Data

VoxNet: A 3D Convolutional Neural Network for real-time object recognition

Spatial Transformer Networks

Multi-view Convolutional Neural Networks for 3D Shape Recognition

Learning Sparse High Dimensional Filters: Image Filtering, Dense CRFs and Bilateral Neural Networks

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification

Very Deep Convolutional Networks for Large-Scale Image Recognition

3D ShapeNets: A deep representation for volumetric shapes

Visualizing and Understanding Convolutional Networks

ImageNet classification with deep convolutional neural networks

Rectified Linear Units Improve Restricted Boltzmann Machines

Approximation capabilities of multilayer feedforward networks

Dropout: a simple way to prevent neural networks from overfitting

A. Outline This supplementary material provides further investigations for the proposed RS-CNN

Field of Study

Computer Science

Journal Information

Name

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Page

5686-5696

Venue Information

Name

Computer Vision and Pattern Recognition

Type

conference

URL

https://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000147

Alternate Names

CVPR
Comput Vis Pattern Recognit

TL;DR

Abstract

Authors

References51 items

SeqViews2SeqLabels: Learning 3D Global Features via Aggregating Sequential Views by RNN With Attention

Multiresolution Tree Networks for 3D Point Cloud Processing

PointSIFT: A SIFT-like Network Module for 3D Point Cloud Semantic Segmentation

RGCNN: Regularized Graph CNN for Point Cloud Segmentation

Attentional ShapeContextNet for Point Cloud Recognition

TL;DR

Abstract

Authors

References51 items

SeqViews2SeqLabels: Learning 3D Global Features via Aggregating Sequential Views by RNN With Attention

Multiresolution Tree Networks for 3D Point Cloud Processing

PointSIFT: A SIFT-like Network Module for 3D Point Cloud Semantic Segmentation

RGCNN: Regularized Graph CNN for Point Cloud Segmentation

Attentional ShapeContextNet for Point Cloud Recognition

GVCNN: Group-View Convolutional Neural Networks for 3D Shape Recognition

Deep Parametric Continuous Convolutional Neural Networks

SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters

Point convolutional neural networks by extension operators

Local Spectral Graph Convolution for Point Set Feature Learning

SO-Net: Self-Organizing Network for Point Cloud Analysis

Flex-Convolution - Million-Scale Point-Cloud Learning Beyond Grid-Worlds

SPLATNet: Sparse Lattice Networks for Point Cloud Processing

Recurrent Slice Networks for 3D Segmentation of Point Clouds

Dynamic Graph CNN for Learning on Point Clouds

PointCNN: Convolution On X-Transformed Points

Adaptive Graph Convolutional Neural Networks

Mining Point Cloud Local Structures by Kernel Correlation and Graph Pooling

Pointwise Convolutional Neural Networks

Relation Networks for Object Detection

Non-local Neural Networks

PCPNet Learning Local Shape Properties from Raw Point Clouds

Generalized Convolutional Neural Networks for Point Cloud Data

O-CNN

DeepShape: Deep-Learned Shape Descriptor for 3D Shape Retrieval

PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space

Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs

Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Models

Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputs

Deep Sets

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentation

Multi-View 3D Object Retrieval With Deep Embedding Network

OctNet: Learning Deep 3D Representations at High Resolutions

A scalable active framework for region annotation in 3D shape collections

Dynamic Filter Networks

Volumetric and Multi-view CNNs for Object Classification on 3D Data

VoxNet: A 3D Convolutional Neural Network for real-time object recognition

Spatial Transformer Networks

Multi-view Convolutional Neural Networks for 3D Shape Recognition

Learning Sparse High Dimensional Filters: Image Filtering, Dense CRFs and Bilateral Neural Networks

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification

Very Deep Convolutional Networks for Large-Scale Image Recognition

3D ShapeNets: A deep representation for volumetric shapes

Visualizing and Understanding Convolutional Networks

ImageNet classification with deep convolutional neural networks

Rectified Linear Units Improve Restricted Boltzmann Machines

Approximation capabilities of multilayer feedforward networks

Dropout: a simple way to prevent neural networks from overfitting

A. Outline This supplementary material provides further investigations for the proposed RS-CNN

Field of Study

Journal Information

Name

Page

Venue Information

Name

Type

URL

Alternate Names