AI Paper Atlas

Research map / Point clouds / Point cloud classification

Structural Relational Reasoning of Point Clouds

Yueqi Duan, Yu Zheng, Jiwen Lu, Jie Zhou, Qi Tian

CVPR 2019 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 114 citations (OpenAlex)

Check 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 SRN to PointNet++PointNet++ · ModelNet40classification accuracy (%): 90.6 -> 91.5Improved
Add SRN to PointNet++PointNet++ · ScanNetclassification accuracy (%): 77.1 -> 79.7Improved
Add SRN to PointNet++PointNet++ · ShapeNet Partmean part IoU (%): 85.1 -> 85.3Improved
Use geometrical relations only and concatenate features (ablation)PointNet++ · ModelNet40classification accuracy (%): 90.6 -> 91.0Improved
Use geometrical relations only with residual fusion (ablation)PointNet++ · ModelNet40classification accuracy (%): 90.6 -> 90.7Improved
Use locational relations only and concatenate features (ablation)PointNet++ · ModelNet40classification accuracy (%): 90.6 -> 91.1Improved
Use locational relations only with residual fusion (ablation)PointNet++ · ModelNet40classification accuracy (%): 90.6 -> 91.2Improved
Use both geometrical and locational relations with concatenation (ablation)PointNet++ · ModelNet40classification accuracy (%): 90.6 -> 91.3Improved
Use both geometrical and locational relations with residual fusion (ablation)PointNet++ · ModelNet40classification accuracy (%): 90.6 -> 91.5Improved
Use residual fusion instead of concatenation when combining both relation types (ablation)SRN-PointNet++ · ModelNet40classification accuracy (%): 91.3 -> 91.5Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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