AI Paper Atlas

Research map / Point clouds / Point cloud classification

Deep Positional and Relational Feature Learning for Rotation-Invariant Point Cloud Analysis

Ruixuan Yu, Xin Wei, Federico Tombari, Jian Sun

ECCV 2020 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 45 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 geometric feature extraction (ablation)PR-invNet · ModelNet40accuracy: 88.2 -> 89.2Improved
add PFE-block (ablation)PR-invNet · ModelNet40accuracy: 87.8 -> 89.2Improved
add RFE-block (ablation)PR-invNet · ModelNet40accuracy: 88.0 -> 89.2Improved
use pose selector instead of average-pooling over all poses (ablation)PFE-block · ModelNet40accuracy: 88.1 -> 88.5Improved
use pose selector instead of max-pooling over all poses (ablation)PFE-block · ModelNet40accuracy: 88.3 -> 88.5Improved
add position term to RFE filter (ablation)RFE-block · ModelNet40accuracy: 88.1 -> 89.2Improved
add geometric feature term to RFE filter (ablation)RFE-block · ModelNet40accuracy: 88.8 -> 89.2Improved
add point feature term to RFE filter (ablation)RFE-block · ModelNet40accuracy: 89.9 -> 89.2Hurt
add geometric-feature-only term g removed from filter (ablation)RFE-block · ModelNet40accuracy: 88.5 -> 89.2Improved
concatenate all PFE and RFE features instead of PFE only (ablation)PR-invNet · ModelNet40accuracy: 88.5 -> 89.2Improved
concatenate all PFE and RFE features instead of RFE only (ablation)PR-invNet · ModelNet40accuracy: 87.4 -> 89.2Improved
use pose selector over rot-space instead of pure PCA alignment (ablation)PR-invNet · ModelNet40 (SO(3)/SO(3))accuracy: 88.3 -> 89.2Improved

Earlier methods this paper compares with

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