AI Paper Atlas

Research map / Point clouds / Point cloud classification

PointVector: A Vector Representation in Point Cloud Analysis

Xin Deng, WenYu Zhang, Qing Ding, XinMing Zhang

CVPR 2023 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 101 citations (OpenAlex)

Read the paper

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 PointNeXt's InvResMLP with VPSA vector-oriented aggregationPointNeXt-XL · S3DIS 6-fold cross-validationmIOU: 74.9 -> 78.4Improved
Replace PointNeXt's InvResMLP with VPSA vector-oriented aggregationPointNeXt-XL · S3DIS Area 5mIOU: 70.8 -> 72.3Improved
Replace PointNeXt-S aggregation with vector-oriented aggregationPointNeXt-S · ScanObjectNN PB_T50_RSOA: 87.7±0.4 -> 87.8±0.4No clear effect
Replace PointNeXt-S aggregation with vector-oriented aggregationPointNeXt-S · ScanObjectNN PB_T50_RSmAcc: 85.8±0.6 -> 86.2±0.5Improved
Use 3D rather than scalar representations (ablation)PointVector-L · S3DIS Area 5mIOU: 69.8 -> 71.2Improved
Use 3D rather than 2D vector representations (ablation)PointVector-L · S3DIS Area 5mIOU: 70.9 -> 71.2Improved
Generate vector representations by rotation-based expansion rather than MLP (ablation)PointVector-L · S3DIS Area 5mIOU: 70.8 -> 71.2Improved
Use sum rather than max reduction with GroupConv (ablation)PointVector-L · S3DIS Area 5mIOU: 70.6 -> 71.2Improved
Use fixed convolution instead of sum+GroupConv (ablation)PointVector-L · S3DIS Area 5mIOU: 71.2 -> 69.4Hurt
Replace vector encoder and vector aggregation with MLP+max+MLPs (ablation)PointVector-XL · S3DIS Area 5mIOU: 71.4 -> 72.3Hurt
Add relative features and positions instead of concatenating them (ablation)PointVector-L · S3DIS Area 5mIOU: 64.9 -> 71.2Improved
Use relative rather than absolute features (ablation)PointVector-L · S3DIS Area 5mIOU: 70.5 -> 71.2Improved

Later papers that compared with this method

1 later accepted paper reports PointVector-XL as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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