Corpus ID: 236447840

CKConv: Learning Feature Voxelization for Point Cloud Analysis

  title={CKConv: Learning Feature Voxelization for Point Cloud Analysis},
  author={Sungmin Woo and Dogyoon Lee and Junhyeop Lee and Sangwon Hwang and Woojin Kim and Sangyoun Lee},
  • Sungmin Woo, Dogyoon Lee, +3 authors Sangyoun Lee
  • Published 2021
  • Computer Science
  • ArXiv
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… Expand

Figures and Tables from this paper


PointConv: Deep Convolutional Networks on 3D Point Clouds
The dynamic filter is extended to a new convolution operation, named PointConv, which can be applied on point clouds to build deep convolutional networks and is able to achieve state-of-the-art on challenging semantic segmentation benchmarks on 3D point clouds. Expand
Interpolated Convolutional Networks for 3D Point Cloud Understanding
A novel Interpolated Convolution operation, InterpConv, is proposed to tackle the point cloud feature learning and understanding problem, to utilize a set of discrete kernel weights and interpolate point features to neighboring kernel-weight coordinates by an interpolation function for convolution. Expand
RGCNN: Regularized Graph CNN for Point Cloud Segmentation
A regularized graph convolutional neural network (RGCNN) that directly consumes point clouds is proposed that significantly reduces the computational complexity while achieving competitive performance with the state of the art. Expand
Local Spectral Graph Convolution for Point Set Feature Learning
This article replaces the standard max pooling step with a recursive clustering and pooling strategy, devised to aggregate information from within clusters of nodes that are close to one another in their spectral coordinates, leading to richer overall feature descriptors. Expand
ShellNet: Efficient Point Cloud Convolutional Neural Networks Using Concentric Shells Statistics
This paper proposes an efficient end-to-end permutation invariant convolution for point cloud deep learning and builds an efficient neural network named ShellNet to directly consume the point clouds with larger receptive fields while maintaining less layers. Expand
Mining Point Cloud Local Structures by Kernel Correlation and Graph Pooling
Two new operations to improve PointNet with a more efficient exploitation of local structures are presented, one focuses on local 3D geometric structures and the other exploits local high-dimensional feature structures by recursive feature aggregation on a nearest-neighbor-graph computed from 3D positions. Expand
KPConv: Flexible and Deformable Convolution for Point Clouds
KPConv is a new design of point convolution, i.e. that operates on point clouds without any intermediate representation, that outperform state-of-the-art classification and segmentation approaches on several datasets. Expand
A-CNN: Annularly Convolutional Neural Networks on Point Clouds
A new method to define and compute convolution directly on 3D point clouds by the proposed annular convolution that can better capture the local neighborhood geometry of each point by specifying the (regular and dilated) ring-shaped structures and directions in the computation. Expand
FPConv: Learning Local Flattening for Point Convolution
FPConv is introduced, a novel surface-style convolution operator designed for 3D point cloud analysis and can be a complementary of volumetric convolutions and jointly training them can further boost overall performance into state-of-the-art results. Expand
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
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. Expand