AI Paper Atlas

Research map / Point clouds / Point cloud classification

A Network Architecture for Point Cloud Classification via Automatic Depth Images Generation

Riccardo Roveri, Lukas Rahmann, Cengiz Oztireli, Markus Gross

CVPR 2018 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 67 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
Add a second learned depth view instead of using one view (ablation)Ours · ModelNet40, random 3D rotationsoverall accuracy: 0.854 -> 0.869Improved
Add a second learned depth view instead of using one view (ablation)Ours · ModelNet40, random y-axis rotationsoverall accuracy: 0.873 -> 0.884Improved
Increase learned depth views from two to four (ablation)Ours · ModelNet40, random 3D rotationsoverall accuracy: 0.869 -> 0.872Improved
Increase learned depth views from two to four (ablation)Ours · ModelNet40, random y-axis rotationsoverall accuracy: 0.884 -> 0.885Improved
Use more than four learned views (ablation)Ours · ModelNet40classification accuracyNo clear effect
Replace learned view prediction with PCA-based view selection (ablation)Ours, one-view architecture · ModelNet40, random 3D rotationsoverall accuracy: 0.854 -> 0.844Hurt
Replace learned view prediction with PCA-based view selection (ablation)Ours, two-view architecture · ModelNet40, random 3D rotationsoverall accuracy: 0.869 -> 0.850Hurt
Replace learned view prediction with random view selection (ablation)Ours, one-view architecture · ModelNet40, random 3D rotationsoverall accuracy: 0.854 -> 0.849Hurt
Replace learned view prediction with random view selection (ablation)Ours, two-view architecture · ModelNet40, random 3D rotationsoverall accuracy: 0.869 -> 0.859Hurt
Replace learned view prediction with random view selection (ablation)Ours, four-view architecture · ModelNet40, random 3D rotationsoverall accuracy: 0.872 -> 0.868Hurt
Replace learned view prediction with random view selection (ablation)Ours, one-view architecture · ModelNet40, random y-axis rotationsoverall accuracy: 0.873 -> 0.849Hurt
Replace learned view prediction with random view selection (ablation)Ours, two-view architecture · ModelNet40, random y-axis rotationsoverall accuracy: 0.884 -> 0.859Hurt

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