AI Paper Atlas

Research map / Point clouds / Point cloud classification

Point2Node: Correlation Learning of Dynamic-Node for Point Cloud Feature Modeling

Wenkai Han, Chenglu Wen, Cheng Wang, Xin Li, Qing Li

AAAI 2020 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 92 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 Point2Node instead of PointWebPoint cloud semantic segmentation · S3DIS 6-fold cross-validationmIoU: 66.73 -> 70.00Improved
Use Point2Node instead of GACNetPoint cloud semantic segmentation · S3DIS Area 5mIoU: 62.85 -> 62.96Improved
Use Point2Node instead of PointWebSemantic voxel labeling · ScanNetOA: 85.9 -> 86.3Improved
Use Point2Node instead of A-CNNShape classification · ModelNet40, 1k xyzOA: 92.6 -> 93.0Improved
Add the self-correlation block (ablation)χ-conv Encoder-Decoder baseline · S3DIS Area 5mIoU: 56.70 -> 57.45Improved
Add the local-correlation block (ablation)χ-conv Encoder-Decoder baseline · S3DIS Area 5mIoU: 56.70 -> 57.91Improved
Add the non-local-correlation block (ablation)χ-conv Encoder-Decoder baseline · S3DIS Area 5mIoU: 56.70 -> 59.74Improved
Use sequential, fully updated correlation blocks instead of placing all blocks in parallel (ablation)Point2Node · S3DIS Area 5mIoU: 59.51 -> 62.96Improved
Use sequential local and non-local blocks rather than parallel local and non-local blocks (ablation)Point2Node · S3DIS Area 5mIoU: 60.57 -> 62.96Improved
Replace adaptive aggregation with linear aggregation (ablation)Point2Node · S3DIS Area 5mIoU: 62.96 -> 58.17Hurt
Use parameterized adaptive aggregation instead of parameter-free adaptive aggregation (ablation)Point2Node · S3DIS Area 5mIoU: 60.57 -> 62.96Improved

Later papers that compared with this method

1 later accepted paper reports Point2Node 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 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