AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Learning Regional Purity for Instance Segmentation on 3D Point Clouds

Shichao Dong, Guosheng Lin, Tzu-Yi Hung

ECCV 2022 · Point clouds › Segmentation and detection · approach: Scene completion and instance segmentation · 16 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 extra grouping radius for high purity points (ablation)baseline clustering · ScanNet v2 valmAP: 0.284 -> 0.294Improved
add extra grouping radius for high purity points (ablation)baseline clustering · ScanNet v2 valmAP@0.5: 0.508 -> 0.518Improved
add low purity points as soft barrier grouped only by medium purity points (ablation)clustering with high purity tolerance · ScanNet v2 valmAP: 0.294 -> 0.322Improved
add low purity points as soft barrier grouped only by medium purity points (ablation)clustering with high purity tolerance · ScanNet v2 valmAP@0.5: 0.518 -> 0.545Improved
shift high purity points by predicted offset (ablation)clustering with purity guidance · ScanNet v2 valmAP: 0.322 -> 0.352Improved
shift high purity points by predicted offset (ablation)clustering with purity guidance · ScanNet v2 valmAP@0.5: 0.545 -> 0.572Improved
add offset direction cosine similarity criterion (ablation)clustering with offset shift · ScanNet v2 valmAP: 0.352 -> 0.359Improved
add offset direction cosine similarity criterion (ablation)clustering with offset shift · ScanNet v2 valmAP@0.5: 0.572 -> 0.582Improved
pretrain on toy scenes instead of training from scratch (ablation)RPGN · ScanNet v2 valmAP: 3.8% mAPImproved
use refined semantic prediction via label smoothingRPGN · ScanNet v2 valmAP@0.5 (avg): 61.9 -> 64.2Improved
use pretrained purity model, evaluate on S3DIS 6-fold instead of Area 5RPGN · S3DISmPrec: 64.0 -> 84.5Improved
replace PointGroup dual-set proposals plus NMS with single-set purity-guided clusteringRPGN · ScanNet v2 valtotal processing time (s): 141 -> 89Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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