AI Paper Atlas

Research map / Point clouds / Point cloud classification

Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds

Huan Lei, Naveed Akhtar, Ajmal Saeed Mian

TPAMI 2020 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 207 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use spherical SPH3D kernel (8x2x2+1 bins) instead of uniform 3x3x3 CNN3D kernel (ablation)graph network · S3DIS Area 5 (2048 points)mIoU: 57.9 -> 61.0Improved
use spherical kernel instead of 5x5x5 CNN3D kernel (ablation)graph network · S3DIS Area 5 (2048 points)mIoU: 58.6 -> 61.0Improved
add self-convolution weight w0 to 3x3x3 CNN3D kernel (ablation)CNN3D kernel · S3DIS Area 5 (2048 points)mIoU: 57.9 -> 58.3No clear effect
add self-convolution weight w0 to 5x5x5 CNN3D kernel (ablation)CNN3D kernel · S3DIS Area 5 (2048 points)mIoU: 58.6 -> 58.3No clear effect
use even-size 4x4x4 kernel (asymmetric) instead of odd 5x5x5 (ablation)CNN3D kernel · S3DIS Area 5 (2048 points)mIoU: 58.6 -> 60.8Improved
use max pooling instead of average pooling (ablation)SPH3D-GCN · S3DIS Area 5 (8192 points)mIoU: 58.8 -> 59.5Improved
add data augmentation (ablation)SPH3D-GCN · S3DIS Area 5 (8192 points)mIoU: 57.0 -> 59.5Improved
use weighted instead of uniform interpolation (dense, 8192 points) (ablation)SPH3D-GCN · S3DIS Area 5 (8192 points)mIoU: 59.5 -> 61.2Improved
use weighted instead of uniform interpolation (sparse, 4096 points) (ablation)SPH3D-GCN · S3DIS Area 5 (4096 points)mIoU: 62.2 -> 61.1Hurt
remove relative location from input (9-dim to 6-dim) (ablation)SPH3D-GCN · S3DIS Area 5mIoU: 58.6 -> 59.5Improved
use separable instead of regular (V1) convolution (ablation)SPH3D-GCN · ModelNet40instance accuracy: 91.3 -> 91.4No clear effect
use separable instead of regular (V1) convolution (ablation)SPH3D-GCN · Random 2048 pointsper-batch time (ms): 36.1 -> 14.0Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy