AI Paper Atlas

Research map / Point clouds / Point cloud classification

SGMNet: Learning Rotation-Invariant Point Cloud Representations via Sorted Gram Matrix

Jianyun Xu, Xin Tang, Yushi Zhu, Jie Sun, Shiliang Pu

ICCV 2021 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 50 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 distance-only features with SGM (ablation)SGMNet · ModelNet40overall accuracy (%): 80.6 -> 90.0Improved
replace angle-only features with SGM (ablation)SGMNet · ModelNet40overall accuracy (%): 85.2 -> 90.0Improved
replace simplified distance+angle PPFs with dense SGM (ablation)SGMNet · ModelNet40overall accuracy (%): 86.6 -> 90.0Improved
combine distance and angle rather than distance alone (ablation)simplified PPF · ModelNet40overall accuracy (%): 80.6 -> 86.6Improved
shrink SGMNet channels from big to mini (ablation)SGMNet · ModelNet40 z/SO(3)overall accuracy (%): 90.0 -> 88.8Mixed
use SGM descriptor in place of xyz coordinates in PointNet++PointNet++ · ModelNet40 z/SO(3)overall accuracy (%): 18.4 -> 90.0Improved
add SGM module to RSCNNRSCNN · ModelNet40overall accuracy (%): 88.5 in all three settingsImproved
add SGM module to DGCNNDGCNN · ModelNet40overall accuracy (%): 92.2 -> 88.9 (z/z), 20.6 -> 88.9 (z/SO(3))Mixed
use SGMNet instead of PointNet++ on part segmentation under arbitrary rotationPointNet++ · ShapeNet part z/SO(3)mIoU (%): 45.9 -> 79.3Improved
use SGMNet instead of PointNet++ in aligned settingPointNet++ · ShapeNet part z/zmIoU (%): 80.6 -> 79.3Hurt

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