Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds (2019-09-20T00:00:00.000000Z)

TL;DR

The proposed spherical kernel for efficient graph convolution of 3D point clouds maintains translation-invariance and asymmetry properties, where the former guarantees weight sharing among similar local structures in the data and the latter facilitates fine geometric learning.

Abstract

We propose a spherical kernel for efficient graph convolution of 3D point clouds. Our metric-based kernels systematically quantize the local 3D space to identify distinctive geometric relationships in the data. Similar to the regular grid CNN kernels, the spherical kernel maintains translation-invariance and asymmetry properties, where the former guarantees weight sharing among similar local structures in the data and the latter facilitates fine geometric learning. The proposed kernel is applied to graph neural networks without edge-dependent filter generation, making it computationally attractive for large point clouds. In our graph networks, each vertex is associated with a single point location and edges connect the neighborhood points within a defined range. The graph gets coarsened in the network with farthest point sampling. Analogous to the standard CNNs, we define pooling and unpooling operations for our network. We demonstrate the effectiveness of the proposed spherical kernel with graph neural networks for point cloud classification and semantic segmentation using ModelNet, ShapeNet, RueMonge2014, ScanNet and S3DIS datasets. The source code and the trained models can be downloaded from https://github.com/hlei-ziyan/SPH3D-GCN.

Authors

Naveed Akhtar

6 papers

A. Mian

8 papers

Huan Lei

1 papers

TL;DR

Abstract

Authors

References98 items

Spherical Fractal Convolutional Neural Networks for Point Cloud Recognition

4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks

KPConv: Flexible and Deformable Convolution for Point Clouds

Octree Guided CNN With Spherical Kernels for 3D Point Clouds

PointConv: Deep Convolutional Networks on 3D Point Clouds

3D Recurrent Neural Networks with Context Fusion for Point Cloud Semantic Segmentation

Monte Carlo convolution for learning on non-uniformly sampled point clouds

Tangent Convolutions for Dense Prediction in 3D

Deep Parametric Continuous Convolutional Neural Networks

Attentional ShapeContextNet for Point Cloud Recognition

SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters

Point convolutional neural networks by extension operators

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

SPLATNet: Sparse Lattice Networks for Point Cloud Processing

Spherical CNNs

Dynamic Graph CNN for Learning on Point Clouds

PointCNN: Convolution On X-Transformed Points

Mining Point Cloud Local Structures by Kernel Correlation and Graph Pooling

Pointwise Convolutional Neural Networks

3D Semantic Segmentation with Submanifold Sparse Convolutional Networks

Large-Scale Point Cloud Semantic Segmentation with Superpoint Graphs

SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels

SEGCloud: Semantic Segmentation of 3D Point Clouds

3D Graph Neural Networks for RGBD Semantic Segmentation

Exploring Spatial Context for 3D Semantic Segmentation of Point Clouds

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

Submanifold Sparse Convolutional Networks

Semantic3D.net: A new Large-scale Point Cloud Classification Benchmark

Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs

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

ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes

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

SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentation

Point cloud labeling using 3D Convolutional Neural Network

Geometric Deep Learning: Going beyond Euclidean data

OctNet: Learning Deep 3D Representations at High Resolutions

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

Xception: Deep Learning with Depthwise Separable Convolutions

Vote3Deep: Fast object detection in 3D point clouds using efficient convolutional neural networks

Semi-Supervised Classification with Graph Convolutional Networks

Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering

3D Semantic Parsing of Large-Scale Indoor Spaces

Efficient 2D and 3D Facade Segmentation Using Auto-Context

Dynamic Filter Networks

FPNN: Field Probing Neural Networks for 3D Data

Orientation-boosted Voxel Nets for 3D Object Recognition

3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions

DeepContext: Context-Encoding Neural Pathways for 3D Holistic Scene Understanding

Deep Residual Learning for Image Recognition

ShapeNet: An Information-Rich 3D Model Repository

SSD: Single Shot MultiBox Detector

Gated Graph Sequence Neural Networks

SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation

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

You Only Look Once: Unified, Real-Time Object Detection

3D all the way: Semantic segmentation of urban scenes from start to end in 3D

Spatial Transformer Networks

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

U-Net: Convolutional Networks for Biomedical Image Segmentation

Multi-view Convolutional Neural Networks for 3D Shape Recognition

FlowNet: Learning Optical Flow with Convolutional Networks

FaceNet: A unified embedding for face recognition and clustering

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

Adam: A Method for Stochastic Optimization

MatConvNet: Convolutional Neural Networks for MATLAB

Fully convolutional networks for semantic segmentation

Dense 3D Face Correspondence

Going deeper with convolutions

Learning Where to Classify in Multi-view Semantic Segmentation

Very Deep Convolutional Networks for Large-Scale Image Recognition

3D ShapeNets: A deep representation for volumetric shapes

Interactive shape co-segmentation via label propagation

Spectral Networks and Locally Connected Networks on Graphs

ImageNet classification with deep convolutional neural networks

3D is here: Point Cloud Library (PCL)

Unique shape context for 3d data description