Papers › Convolution in the Cloud: Learning Deformable Kernels in 3D Graph Convolution Networks...

Convolution in the Cloud: Learning Deformable Kernels in 3D Graph Convolution Networks for Point Cloud Analysis

1 Jun 2020CVPR 2020 6archive 2025-07-28

Zhi-Hao Lin, Sheng-Yu Huang, Yu-Chiang Frank Wang

Point clouds are among the popular geometry representations for 3D vision applications. However, without regular structures like 2D images, processing and summarizing information over these unordered data points are very challenging. Although a number of previous works attempt to analyze point clouds and achieve promising performances, their performances would degrade significantly when data variations like shift and scale changes are presented. In this paper, we propose 3D Graph Convolution Networks (3D-GCN), which is designed to extract local 3D features from point clouds across scales, while shift and scale-invariance properties are introduced. The novelty of our 3D-GCN lies in the definition of learnable kernels with a graph max-pooling mechanism. We show that 3D-GCN can be applied to 3D classification and segmentation tasks, with ablation studies and visualizations verifying the design of 3D-GCN.

PaperPDFCode

Code

j1a0m0e4sNTU/3dgcn officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

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

Tasks

3D Classification3D Part Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Part Segmentation ShapeNet-Part 3D-GCN Class Average IoU 82.1 #54 of 67 Archive leaderboard report
3D Part Segmentation ShapeNet-Part 3D-GCN Instance Average IoU 85.1 #54 of 67 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

Convolution

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