AI Paper Atlas

Research map / Point clouds / Point cloud classification

PointMixup: Augmentation for Point Clouds

Yunlu Chen, Vincent Tao Hu, Efstratios Gavves, Thomas Mensink, Pascal Mettes, Pengwan Yang, Cees G. M. Snoek

ECCV 2020 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 170 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 PointMixup (optimal assignment) interpolation (ablation)PointNet++ · ModelNet40 full, unalignedaccuracy: 90.7 -> 91.3Improved
add manifold mixup to PointMixup (ablation)PointNet++ · ModelNet40 reduced (20%), pre-alignedaccuracy: 87.6 -> 88.6Improved
use PointMixup instead of random assignment interpolation (ablation)PointNet++ · ModelNet40 reduced (20%), pre-alignedaccuracy: 85.5 -> 87.6Improved
use PointMixup instead of point sampling interpolation (ablation)PointNet++ · ModelNet40 full, pre-alignedaccuracy: 92.2 -> 92.3Improved
random assignment mixup instead of no mixup (ablation)PointNet++ · ModelNet40 full, pre-alignedaccuracy: 91.9 -> 91.6Hurt
PointMixup versus label smoothing (0.2) (ablation)PointNet++ · ModelNet40 reduced (20%), pre-alignedaccuracy: 87.3 -> 88.6Improved
mix input only, not labels (ablation)PointMixup · ModelNet40 reduced (20%), pre-alignedaccuracy: 88.6 -> 86.6Hurt
mix input from same class only (ablation)PointMixup · ModelNet40 reduced (20%), pre-alignedaccuracy: 88.6 -> 86.4Hurt
mix latent at fixed layer 1 instead of random layers (ablation)PointMixup · ModelNet40 reduced (20%), pre-alignedaccuracy: 88.6 -> 86.9Hurt
add manifold mixup (ablation)PointMixup · ModelNet40 noise sigma^2=0.05accuracy: 35.1 -> 56.5Improved
add manifold mixup (ablation)PointMixup · ModelNet40 scale 2.0accuracy: 59.2 -> 72.9Improved
PointMixup without manifold mixup under Z-rotation (ablation)PointNet++ · ModelNet40 Z-rotation [-30,30]accuracy: 74.3 -> 70.9Hurt

Later papers that compared with this method

2 later accepted papers report PointMixup as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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