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

Published in

Computer Vision and Pattern Recognition(2016)

External Links:

Generate Graph DownloadPDF

TL;DR

This paper designs a novel type of neural network that directly consumes point clouds, which well respects the permutation invariance of points in the input and provides a unified architecture for applications ranging from object classification, part segmentation, to scene semantic parsing.

Abstract

Point cloud is an important type of geometric data structure. Due to its irregular format, most researchers transform such data to regular 3D voxel grids or collections of images. This, however, renders data unnecessarily voluminous and causes issues. In this paper, we design a novel type of neural network that directly consumes point clouds, which well respects the permutation invariance of points in the input. Our network, named PointNet, provides a unified architecture for applications ranging from object classification, part segmentation, to scene semantic parsing. Though simple, PointNet is highly efficient and effective. Empirically, it shows strong performance on par or even better than state of the art. Theoretically, we provide analysis towards understanding of what the network has learnt and why the network is robust with respect to input perturbation and corruption.

Authors

C. Qi

15 papers

Hao Su

10 papers

Kaichun Mo

5 papers

References34 items

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

3D Semantic Parsing of Large-Scale Indoor Spaces

FPNN: Field Probing Neural Networks for 3D Data

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

TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems

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

Published in

Computer Vision and Pattern Recognition(2016)

External Links:

Generate Graph DownloadPDF

TL;DR

Abstract

Authors

C. Qi

15 papers

Hao Su

10 papers

Kaichun Mo

5 papers

References34 items

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

3D Semantic Parsing of Large-Scale Indoor Spaces

FPNN: Field Probing Neural Networks for 3D Data

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

TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems

3D Mesh Labeling via Deep Convolutional Neural Networks

Order Matters: Sequence to sequence for sets

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

Voting for Voting in Online Point Cloud Object Detection

3D deep shape descriptor

Spatial Transformer Networks

Multi-view Convolutional Neural Networks for 3D Shape Recognition

Geodesic Convolutional Neural Networks on Riemannian Manifolds

3D ShapeNets: A deep representation for volumetric shapes

Interactive shape co-segmentation via label propagation

Spectral Networks and Locally Connected Networks on Graphs

The wave kernel signature: A quantum mechanical approach to shape analysis

BlenSor: Blender Sensor Simulation Toolbox

Scale-invariant heat kernel signatures for non-rigid shape recognition

Fast Point Feature Histograms (FPFH) for 3D registration

Aligning point cloud views using persistent feature histograms

Shape Classification Using the Inner-Distance

On Visual Similarity Based 3D Model Retrieval

Best practices for convolutional neural networks applied to visual document analysis

Rotation Invariant Spherical Harmonic Representation of 3D Shape Descriptors

Using Spin Images for Efficient Object Recognition in Cluttered 3D Scenes

SHREC’16 Track Large-Scale 3D Shape Retrieval from ShapeNet Core55

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition-' Washington , D . C . , June , 1983 OPTIMAL PERCEPTUAL INFERENCE

Visualizing Data using t-SNE

GradientBased Learning Applied to Document Recognition

Gradient-based learning applied to document recognition

Eurographics Symposium on Geometry Processing 2009 a Concise and Provably Informative Multi-scale Signature Based on Heat Diffusion

Semantic segmentation is not that accurate, with only 47% mIoU, where the ones nowadays can achieve over 80%

It provides a unified approach to a number of 3D recognition tasks including object classification, part segmentation and semantic segmentation

Field of Study

Computer Science

Journal Information

Name

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Page

77-85

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