.png){kind=icon}
.png){kind=icon}
Return
MKConv: Multidimensional feature representation for point cloud analysis
.png){kind=icon}
OA
AI
DOI：10.1016/j.patcog.2023.109800.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Despite the remarkable success of deep learning, an optimal convolution operation on point clouds re-mains elusive owing to their irregular data structure. Existing methods mainly focus on designing an effective continuous kernel function that can handle an arbitrary point in continuous space. Various ap-proaches exhibiting high performance have been proposed, but we observe that the standard pointwise feature is represented by 1D channels and can become more informative when its representation in-volves additional spatial feature dimensions. In this paper, we present Multidimensional Kernel Convo-lution (MKConv), a novel convolution operator that learns to transform the point feature representation from a vector to a multidimensional matrix. Unlike standard point convolution, MKConv proceeds via two steps. (i) It first activates the spatial dimensions of local feature representation by exploiting multi-dimensional kernel weights. These spatially expanded features can represent their embedded information through spatial correlation as well as channel correlation in feature space, carrying more detailed local structure information. (ii) Then, discrete convolutions are applied to the multidimensional features which can be regarded as a grid-structured matrix. In this way, we can utilize the discrete convolutions for point cloud data without voxelization that suffers from information loss. Furthermore, we propose a spatial at-tention module, Multidimensional Local Attention (MLA), to provide comprehensive structure awareness within the local point set by reweighting the spatial feature dimensions. We demonstrate that MKConv has excellent applicability to point cloud processing tasks including object classification, object part seg-mentation, and scene semantic segmentation with superior results. & COPY; 2023 Elsevier Ltd. All rights reserved.
Keywords:
Point cloud
Feature learning
Convolutional neural network
3D vision
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.