diffConv: Analyzing Irregular Point Clouds with an Irregular View

11/29/2021
by   Manxi Lin, et al.
0

Standard spatial convolutions assume input data with a regular neighborhood structure. Existing methods typically generalize convolution to the irregular point cloud domain by fixing a regular "view" through e.g. a fixed neighborhood size, where the convolution kernel size remains the same for each point. However, since point clouds are not as structured as images, the fixed neighbor number gives an unfortunate inductive bias. We present a novel graph convolution named Difference Graph Convolution (diffConv), which does not rely on a regular view. diffConv operates on spatially-varying and density-dilated neighborhoods, which are further adapted by a learned masked attention mechanism. We validate our model on the ModelNet40 point cloud classification benchmark, obtaining state-of-the-art performance and far more robustness to noise, along with a much faster inference speed.

READ FULL TEXT
research
11/17/2018

PointConv: Deep Convolutional Networks on 3D Point Clouds

Unlike images which are represented in regular dense grids, 3D point clo...
research
04/18/2019

KPConv: Flexible and Deformable Convolution for Point Clouds

We present Kernel Point Convolution (KPConv), a new design of point conv...
research
03/20/2018

Flex-Convolution (Deep Learning Beyond Grid-Worlds)

The goal of this work is to enable deep neural networks to learn represe...
research
01/19/2021

The Devils in the Point Clouds: Studying the Robustness of Point Cloud Convolutions

Recently, there has been a significant interest in performing convolutio...
research
08/04/2022

PointConvFormer: Revenge of the Point-based Convolution

We introduce PointConvFormer, a novel building block for point cloud bas...
research
04/21/2022

TorchSparse: Efficient Point Cloud Inference Engine

Deep learning on point clouds has received increased attention thanks to...
research
08/07/2022

Global Hierarchical Attention for 3D Point Cloud Analysis

We propose a new attention mechanism, called Global Hierarchical Attenti...

Please sign up or login with your details

Forgot password? Click here to reset