AI Paper Atlas

Research map / Point clouds / Point cloud classification

OctNet: Learning Deep 3D Representations at High Resolutions

Gernot Riegler, Ali Osman Ulusoy, Andreas Geiger

CVPR 2017 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 1,716 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
Increase input resolution from 64^3 to 256^3OctNet · RueMonge2014IoU: 45.6 -> 59.2Improved
Increase input resolution from 64^3 to 256^3OctNet · RueMonge2014average class accuracy: 60.0 -> 73.6Improved
Increase input resolution from 64^3 to 256^3OctNet · RueMonge2014overall pixel accuracy: 73.6 -> 81.5Improved
Increase input resolution beyond 32^3OctNet with fixed model capacity · ModelNet10classification accuracyNo clear effect
Increase input resolution beyond 32^3OctNet · ModelNet40classification accuracyNo clear effect
Increase input resolutionOctNet · ModelNet10 chair orientation estimationmean angular errorImproved
Increase input resolution from 8^3 to 64^3OctNet · Biwi Kinect Head Pose Databaseorientation accuracyImproved
Use higher input resolutionOctNet · 3D object classificationclassification accuracyMixed

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