CKConv: Learning Feature Voxelization for Point Cloud Analysis

07/27/2021
by   Sungmin Woo, et al.
9

Despite the remarkable success of deep learning, optimal convolution operation on point cloud remains indefinite due to its irregular data structure. In this paper, we present Cubic Kernel Convolution (CKConv) that learns to voxelize the features of local points by exploiting both continuous and discrete convolutions. Our continuous convolution uniquely employs a 3D cubic form of kernel weight representation that splits a feature into voxels in embedding space. By consecutively applying discrete 3D convolutions on the voxelized features in a spatial manner, preceding continuous convolution is forced to learn spatial feature mapping, i.e., feature voxelization. In this way, geometric information can be detailed by encoding with subdivided features, and our 3D convolutions on these fixed structured data do not suffer from discretization artifacts thanks to voxelization in embedding space. Furthermore, we propose a spatial attention module, Local Set Attention (LSA), to provide comprehensive structure awareness within the local point set and hence produce representative features. By learning feature voxelization with LSA, CKConv can extract enriched features for effective point cloud analysis. We show that CKConv has great applicability to point cloud processing tasks including object classification, object part segmentation, and scene semantic segmentation with state-of-the-art results.

READ FULL TEXT

page 4

page 7

research
08/13/2019

Interpolated Convolutional Networks for 3D Point Cloud Understanding

Point cloud is an important type of 3D representation. However, directly...
research
02/25/2020

FPConv: Learning Local Flattening for Point Convolution

We introduce FPConv, a novel surface-style convolution operator designed...
research
06/07/2019

PyramNet: Point Cloud Pyramid Attention Network and Graph Embedding Module for Classification and Segmentation

With the tide of artificial intelligence, we try to apply deep learning ...
research
04/05/2021

Potential Convolution: Embedding Point Clouds into Potential Fields

Recently, various convolutions based on continuous or discrete kernels f...
research
01/17/2021

Deep Parametric Continuous Convolutional Neural Networks

Standard convolutional neural networks assume a grid structured input is...
research
07/27/2023

Clustering based Point Cloud Representation Learning for 3D Analysis

Point cloud analysis (such as 3D segmentation and detection) is a challe...
research
03/13/2020

Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation

Online semantic 3D segmentation in company with real-time RGB-D reconstr...

Please sign up or login with your details

Forgot password? Click here to reset