AI Paper Atlas

Research map / Point clouds / Point cloud classification

Local Spectral Graph Convolution for Point Set Feature Learning

Chu Wang, Babak Samari, Kaleem Siddiqi

ECCV 2018 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 406 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
replace point-MLP with spectral graph convolution on local kNN graph (ablation)4l-pointnet++ · ModelNet40 (1k xyz)accuracy: 90.6 -> 91.2Improved
replace max pooling with recursive cluster pooling (ablation)4l-spec-max · ModelNet40 (1k xyz)accuracy: 91.2 -> 91.5Improved
replace max pooling with recursive cluster pooling (ablation)4l-spec-max · ModelNet40 (2k xyz + normals)accuracy: 91.9 -> 92.1Improved
add surface normals to xyz input (ablation)4l-spec-cp · ModelNet40accuracy: 91.5 -> 91.8Improved
increase input points from 1k to 2k (with normals) (ablation)4l-spec-cp · ModelNet40accuracy: 91.8 -> 92.1Improved
use 3 layers instead of 4 layers (ablation)pointnet++ · ModelNet40 (1k xyz)accuracy: 90.6 -> 90.7Improved
add spectral graph convolution and cluster pooling to pointnet++ (ablation)3l-pointnet++ · ShapeNet part seg (2k xyz + normals)mIoU: 84.9 -> 85.4Improved
add spectral graph convolution and cluster pooling to pointnet++ (ablation)3l-pointnet++ · ShapeNet part seg (1k xyz)mIoU: 84.2 -> 84.6Improved
replace max pooling with recursive cluster pooling (ablation)4l-spec · McGill Shape Benchmark (combined)instance accuracy: 95.14 -> 95.83Improved
replace point-MLP with spectral convolution (ablation)4l-pointnet++ · McGill Shape Benchmark (combined)instance accuracy: 92.36 -> 95.14Improved
replace point-MLP with spectral graph convolution plus cluster pooling (ablation)3l-pointnet++ · MNISTerror rate (%): 0.55 -> 0.42Improved
use spectral graph convolution plus cluster pooling (ablation)4l-pointnet++ · ScanNetaccuracy: 84.0 -> 84.8Improved

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