AI Paper Atlas

Research map / Point clouds / Point cloud classification

Group Contextual Encoding for 3D Point Clouds

Xu Liu, Chengtao Li, Jian Wang, Jingbo Wang, Boxin Shi, Xiaodong He

NeurIPS 2020 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 3 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 SA2 with SA2' using global average pooling (K=0, G=1) (ablation)PointNet++ VoteNet · ScanNet V2mAP@0.25: 51.2 -> 51.7Improved
Add encoding layer with K=8 code words (G=1) (ablation)SA2 · SUN RGB-D V1mAP@0.25: 51.2 -> 54.6Improved
Increase code words from K=8 to K=32 (G=1) (ablation)SA2' · ScanNet V2mAP@0.25: 53.0 -> 53.4No clear effect
Increase code words from K=8 to K=24 (G=1) (ablation)SA2' · SUN RGB-D V1mAP@0.25: 54.6 -> 55.5Improved
Multiply channel number by 2 without encoding (ablation)SA2 · SUN RGB-DmAP@0.25: 51.2 -> 54.0Improved
Multiply channel number by 3 without encoding (ablation)SA2 · SUN RGB-DmAP@0.25: 51.2 -> 54.2Improved
Replace encoding layer (G=1) with group division (G=12) (ablation)SA2' C x 3 · SUN RGB-DmAP@0.25: 55.8 -> 57.1Improved
Add encoding layer (G=1) on C x 3 baseline (ablation)SA2 C x 3 · SUN RGB-DmAP@0.25: 54.2 -> 55.8Improved
Add channel shuffle to grouping (ablation)Group contextual encoding C x 3 · SUN RGB-DmAP@0.25: 57.1 -> 56.3Hurt
Group contextual encoding vs original SA layer at C x 3 (ablation)PointNet++ · SUN RGB-DmAP@0.25: 54.2 -> 57.1Improved
Add group contextual encoding blocks to VoteNetVoteNet · ScanNet V2mAP@0.5: 33.54 -> 40.11Improved
Add group contextual encoding blocks to VoteNetVoteNet · ScanNet V2mAP@0.25: 58.65 -> 60.83Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 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