AI Paper Atlas

Research map / Point clouds / Point cloud classification

3D-Rotation-Equivariant Quaternion Neural Networks

Wen Shen, Binbin Zhang, Shikun Huang, Zhihua Wei, Quanshi Zhang

ECCV 2020 · Point clouds › Point cloud classification · approach: Equivariant point cloud networks · 57 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
revise PointNet++ into a rotation-equivariant quaternion network (REQNN)PointNet++ · ModelNet40 (tested with arbitrary rotations)accuracy: 23.57 -> 63.95Improved
revise DGCNN into a REQNNDGCNN · ModelNet40 (tested with arbitrary rotations)accuracy: 30.05 -> 83.03Improved
revise PointConv into a REQNNPointConv · ModelNet40 (tested with arbitrary rotations)accuracy: 21.93 -> 78.14Improved
revise PointNet++ into a REQNNPointNet++ · 3D MNIST (tested with arbitrary rotations)accuracy: 44.15 -> 68.99Improved
revise DGCNN into a REQNNDGCNN · 3D MNIST (tested with arbitrary rotations)accuracy: 45.37 -> 82.09Improved
revise PointConv into a REQNNPointConv · 3D MNIST (tested with arbitrary rotations)accuracy: 44.63 -> 78.59Improved
add z-axis rotation data augmentation to baseline training (ablation)PointNet++, DGCNN, PointConv · ModelNet40 (tested with arbitrary rotations)accuracy: 23.57 -> 26.43; 30.05 -> 31.34; 21.93 -> 23.72No clear effect
add z-axis rotation data augmentation to baseline training (ablation)PointNet++, DGCNN, PointConv · 3D MNIST (tested with arbitrary rotations)accuracy: 44.15 -> 51.16; 45.37 -> 49.25; 44.63 -> 50.95Improved
switch from standard DGCNN to REQNN when test rotations are introducedDGCNN · ModelNet40 NR/NR vs NR/ARaccuracy: 92.90 -> 83.03 (NR/NR); 29.74 -> 83.03 (NR/AR)Mixed
use REQNN instead of PRIN and QE-Capsule network under arbitrary test rotationsREQNN (DGCNN) · ModelNet40 NR/ARaccuracy: 68.85 -> 83.03; 74.07 -> 83.03Improved
revise original networks into REQNNs (computational cost)PointNet++, DGCNN, PointConv · ModelNet40 complexityFLOPs (G): 0.87 -> 2.51; 3.53 -> 8.24; 1.44 -> 4.22Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 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