SOTAVerified

Point Cloud Classification

Point Cloud Classification is a task involving the classification of unordered 3D point sets (point clouds).

Papers

Showing 5175 of 265 papers

TitleStatusHype
Point Cloud Augmentation with Weighted Local TransformationsCode1
Self-supervised Point Cloud Representation Learning via Separating Mixed ShapesCode1
Geometry-Aware Self-Training for Unsupervised Domain Adaptationon Object Point CloudsCode1
Surrogate Model-Based Explainability Methods for Point Cloud NNsCode1
Revisiting Point Cloud Shape Classification with a Simple and Effective BaselineCode1
Image2Point: 3D Point-Cloud Understanding with 2D Image Pretrained ModelsCode1
Walk in the Cloud: Learning Curves for Point Clouds Shape AnalysisCode1
Zero-Shot Learning on 3D Point Cloud Objects and BeyondCode1
PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point CloudsCode1
Regularization Strategy for Point Cloud via Rigidly Mixed SampleCode1
PointCutMix: Regularization Strategy for Point Cloud ClassificationCode1
Revisiting Point Cloud Classification with a Simple and Effective BaselineCode1
Geometry-Aware Self-Training for Unsupervised Domain Adaptation on Object Point CloudsCode1
Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point CloudCode1
PCT: Point cloud transformerCode1
RobustPointSet: A Dataset for Benchmarking Robustness of Point Cloud ClassifiersCode1
Unsupervised Point Cloud Pre-Training via Occlusion CompletionCode1
PointMixup: Augmentation for Point CloudsCode1
Point Set Voting for Partial Point Cloud AnalysisCode1
Parameter-Efficient Person Re-identification in the 3D SpaceCode1
Dense-Resolution Network for Point Cloud Classification and SegmentationCode1
MOPS-Net: A Matrix Optimization-driven Network forTask-Oriented 3D Point Cloud DownsamplingCode1
Generative PointNet: Deep Energy-Based Learning on Unordered Point Sets for 3D Generation, Reconstruction and ClassificationCode1
PointAugment: an Auto-Augmentation Framework for Point Cloud ClassificationCode1
PointHop++: A Lightweight Learning Model on Point Sets for 3D ClassificationCode1
Show:102550
← PrevPage 3 of 11Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1PointNetmean Corruption Error (mCE)1.42Unverified
2WOLFMix (PointNet)mean Corruption Error (mCE)1.18Unverified
3PointNetmean Corruption Error (mCE)1.18Unverified
4RSCNNmean Corruption Error (mCE)1.13Unverified
5PAConvmean Corruption Error (mCE)1.1Unverified
6SimpleViewmean Corruption Error (mCE)1.05Unverified
7OcCo-DGCNNmean Corruption Error (mCE)1.05Unverified
8PointMixUp (PointNet++)mean Corruption Error (mCE)1.03Unverified
9DGCNNmean Corruption Error (mCE)1Unverified
10OcCo-DGCNNmean Corruption Error (mCE)0.98Unverified
#ModelMetricClaimedVerifiedStatus
1OursAverage F182.8Unverified