AI Paper Atlas

Research map / Point clouds / Point cloud classification

Attention-Based Point Cloud Edge Sampling

Chengzhi Wu, Junwei Zheng, Julius Pfrommer, Jürgen Beyerer

CVPR 2023 · Point clouds › Point cloud classification · approach: Efficient point sampling architectures · 103 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 global-based APES instead of local-based APESAPES classification model · ModelNet40overall accuracy: 93.5% -> 93.8%Improved
Use APES global sampling rather than the strongest reported baseline sampling methodPointNet sampling evaluation · ModelNet40 classification, 32 pointsaccuracy: 86.18 -> 88.56Improved
Use N2P attention instead of EdgeConv for feature learning (ablation)APES local · ModelNet40overall accuracy: 93.02 -> 93.47Improved
Use N2P attention instead of P2P attention for feature learning (ablation)APES local · ModelNet40overall accuracy: 93.30 -> 93.47Improved
Use N2P attention instead of EdgeConv for feature learning (ablation)APES global · ModelNet40overall accuracy: 93.18 -> 93.81Improved
Use N2P attention instead of P2P attention for feature learning (ablation)APES global · ModelNet40overall accuracy: 93.46 -> 93.81Improved
Increase embedding dimension from 64 to 128 (ablation)APES local · ModelNet40overall accuracy: 93.10 -> 93.47Improved
Increase embedding dimension from 128 to 192 (ablation)APES local · ModelNet40overall accuracy: 93.47 -> 93.54Improved
Increase embedding dimension from 64 to 128 (ablation)APES global · ModelNet40overall accuracy: 93.34 -> 93.81Improved
Increase embedding dimension from 128 to 192 (ablation)APES global · ModelNet40overall accuracy: 93.81 -> 93.83Improved
Increase local neighborhood size from k=8 to k=32 (ablation)APES local · ModelNet40overall accuracy: 93.14 -> 93.47Improved
Increase local neighborhood size from k=32 to k=512 (ablation)APES local · ModelNet40overall accuracy: 93.47 -> 93.63Improved

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