AI Paper Atlas

Research map / Point clouds / Point cloud classification

Pyramid Point Cloud Transformer for Large-Scale Place Recognition

Le Hui, Hang Yang, Mingmei Cheng, Jin Xie, Jian Yang

ICCV 2021 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 153 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
replace PointNet++ with the pyramid point transformer (ablation)PPT-Net · OxfordAR@1%: 94.4 -> 98.1Improved
add local k-NN graph embedding (ablation)PPT-Net · OxfordAR@1%: 96.0 -> 98.1Improved
add transformer (ablation)PPT-Net · OxfordAR@1%: 97.3 -> 98.1Improved
use grouped self-attention with G = 8 instead of G = 1 (ablation)PPT-Net · OxfordAR@1% and FLOPs: 97.5 -> 98.1Improved
increase groups from G = 8 to G = 16 (ablation)PPT-Net · OxfordAR@1%: 98.1 -> 97.4Hurt
use all four resolutions in pyramid VLAD instead of a single scale (ablation)PPT-Net · OxfordrecallImproved
vary k of the local k-NN graph (ablation)PPT-Net · OxfordrecallNo clear effect
use PPT-Net instead of MinkLoc3DMinkLoc3D · Oxford (trained on baseline dataset)AR@1%: 95.9 -> 98.1Improved
use PPT-Net instead of MinkLoc3D with data augmentationMinkLoc3D with data augmentation · Oxford AR@1AR@1: 93.7 -> 93.5Hurt
add handcrafted features to LPD-NetLPD-Net · U.S. (in-house)AR@1%: 85.7 -> 96.0Improved
add data augmentation to MinkLoc3DMinkLoc3D · OxfordAR@1%: 95.9 -> 97.9Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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