AI Paper Atlas

Research map / Point clouds / Point cloud classification

RIConv++: Effective Rotation Invariant Convolutions for 3D Point Clouds Deep Learning

Zhiyuan Zhang, Binh‐Son Hua, Sai-Kit Yeung

IJCV 2022 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 70 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
add neighbor-neighbor relation features to IRIF (ablation)RIConv++ · ModelNet40accuracy: 88.4 -> 91.2Improved
add distance features alongside angle features (ablation)RIConv++ · ModelNet40accuracy: 90.5 -> 91.2Improved
add angle features alongside distance features (ablation)RIConv++ · ModelNet40accuracy: 83.3 -> 91.2Improved
increase kernel size from 1 to 3 (ablation)RIConv++ · ModelNet40accuracy: 91.2 -> 91.2No clear effect
increase kernel size from 1 to 7 (ablation)RIConv++ · ModelNet40accuracy: 91.2 -> 91.0Hurt
replace xyz input with IRIF featuresPointNet++ · ModelNet40 (z/SO3)accuracy: 28.6 -> 89.0Improved
replace xyz input with IRIF featuresDGCNN · ModelNet40 (z/SO3)accuracy: 20.6 -> 90.2Improved
replace xyz input with IRIF featuresDGCNN · ModelNet40 (z/z)accuracy: 92.2 -> 90.2Hurt
use IRIF with LRA instead of RIConv featuresRIConv · ModelNet40 (3-layer)accuracy: 86.5 -> 89.8Improved
use IRIF instead of LRF-transform features of GCAConvGCAConv · ModelNet40 (3-layer)accuracy: 89.0 -> 89.8Improved
use normal vectors as reference axis instead of LRARIConv++ · ModelNet40accuracy: 91.2 -> 91.3No clear effect
add background points to objects (OBJ_ONLY to OBJ_BG)RIConv++ · ScanObjectNN (z/z)accuracy: 86.2 -> 85.6No clear effect

Later papers that compared with this method

2 later accepted papers report RIConv++ as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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