AI Paper Atlas

Research map / Point clouds / Point cloud classification

PnP-3D: A Plug-and-Play for 3D Point Clouds

Shi Qiu, Saeed Anwar, Nick M. Barnes

TPAMI 2021 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 49 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 PnP-3D modulePointNet++ · ScanObjectNNoverall accuracy: 77.9 -> 82.2Improved
add PnP-3D modulePointNet++ · ModelNet40overall accuracy: 90.7 -> 93.2Improved
add PnP-3D modulePAConv · ModelNet40overall accuracy: 93.6 -> 93.8Improved
add PnP-3D modulefour segmentation baselines · S3DIS Area 5mIoU: 2.7% to 5.2% mIoUImproved
add PnP-3D modulethree detection baselines · SUN RGB-D V1mAP: 1.4% to 1.7% mAPImproved
use average-pooling with subtraction instead of max-pooling with product (ablation)PnP-3D on RandLA-Net · S3DIS Area 5mIoU: 63.0 -> 65.5Improved
use average-pooling instead of max-pooling (subtraction regularization) (ablation)PnP-3D on RandLA-Net · S3DIS Area 5mIoU: 63.3 -> 65.5Improved
use geometric mean for global response instead of sum (ablation)PnP-3D on RandLA-Net · S3DIS Area 5mIoU: 64.7 -> 65.5Improved
use geometric mean instead of grand mean for global response (ablation)PnP-3D on RandLA-Net · S3DIS Area 5mIoU: 63.7 -> 65.5Improved
use PnP-3D instead of other attention modules (A-SCN) (ablation)VoteNet · SUN RGB-D V1mAP@0.25: 55.6 -> 59.1Improved
use PnP-3D instead of Point-Transformer (ablation)VoteNet · SUN RGB-D V1mAP@0.25: 58.1 -> 59.1Improved
use PnP-3D instead of additional RGB color inputVoteNet · SUN RGB-D V1mAP: 56.3 -> 59.1Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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