Papers › MKConv: Multidimensional Feature Representation for Point Cloud Analysis

MKConv: Multidimensional Feature Representation for Point Cloud Analysis

27 Jul 2021arXiv:2107.12655archive 2025-07-28

Sungmin Woo, Dogyoon Lee, Sangwon Hwang, Woojin Kim, Sangyoun Lee

Despite the remarkable success of deep learning, an optimal convolution operation on point clouds remains 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 approaches 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 involves additional spatial feature dimensions. In this paper, we present Multidimensional Kernel Convolution (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 multidimensional 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 attention 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 segmentation, and scene semantic segmentation with superior results.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Part Segmentation3D Point Cloud ClassificationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Part Segmentation ShapeNet-Part MKConv Instance Average IoU 86.7 #16 of 67 Archive leaderboard report
3D Point Cloud Classification ModelNet40 MKConv Number of params 5.63M #34 of 111 Archive leaderboard report
3D Point Cloud Classification ModelNet40 MKConv Overall Accuracy 94.0 #34 of 111 Archive leaderboard report
Semantic Segmentation S3DIS Area5 MKConv mAcc 75.1 #39 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 MKConv mIoU 67.7 #39 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 MKConv oAcc 89.6 #39 of 61 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

CKConvConvolution

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections