AI Paper Atlas

Research map / Point clouds / Point cloud classification

PRIN/SPRIN: On Extracting Point-Wise Rotation Invariant Features

Yang You, Yujing Lou, Ruoxi Shi, Qi Liu, Yu‐Wing Tai, Lizhuang Ma, Weiming Wang, Cewu Lu

TPAMI 2021 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 28 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 density aware adaptive sampling (DAAS) instead of uniform sampling (ablation)PRIN · ShapeNet part, rotatedmIoU: 67.47 -> 71.20Improved
use density aware adaptive sampling (DAAS) instead of uniform sampling (ablation)PRIN · ShapeNet part, rotatedaccuracy: 83.13 -> 85.99Improved
increase bandwidth from 4 to 32 (ablation)PRIN · ShapeNet part, rotatedaccuracy and mIoU: 72.20/52.98 -> 85.99/71.20Improved
increase bandwidth from 16 to 32 (ablation)PRIN · ShapeNet part, rotatedmIoU: 68.09 -> 71.20Improved
add triangle features to correlation features (ablation)SPRIN · ShapeNet part, rotatedmIoU: 79.70 -> 82.67Improved
add correlation features to triangle features (ablation)SPRIN · ShapeNet part, rotatedmIoU: 81.38 -> 82.67Improved
reduce input points from 2048 to 1024 (ablation)SPRIN · ShapeNet part, rotatedmIoU: 82.67 -> 79.79Hurt
reduce input points from 2048 to 256 (ablation)PRIN · ShapeNet part, rotatedmIoU: 71.20 -> 36.80Hurt
use sparse SPRIN instead of dense PRINPRIN · ShapeNet part, rotatedavg instance IoU: 71.20 -> 82.67Improved
test on rotated rather than non-rotated shapesSPRIN · ShapeNet partavg instance IoU: 82.59 -> 82.67No clear effect
test on rotated rather than non-rotated shapesPointNet++ · ShapeNet partavg instance IoU: 84.63 -> 36.66Hurt
test on arbitrary rotations rather than noneSPRIN · ModelNet40accuracy: 86.01 -> 86.13No clear effect

Earlier methods this paper compares with

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