SOTAVerified

Point Cloud Classification

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

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 26–50 of 265 papers

TitleStatusHype
Dynamic Local Feature Aggregation for Learning on Point CloudsCode1
ViewNet: A Novel Projection-Based Backbone With View Pooling for Few-Shot Point Cloud ClassificationCode1
Implicit Convolutional Kernels for Steerable CNNsCode1
TetraSphere: A Neural Descriptor for O(3)-Invariant Point Cloud AnalysisCode1
MATE: Masked Autoencoders are Online 3D Test-Time LearnersCode1
APSNet: Attention Based Point Cloud SamplingCode1
CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-trainingCode1
Rethinking the compositionality of point clouds through regularization in the hyperbolic spaceCode1
Scalable Set Encoding with Universal Mini-Batch Consistency and Unbiased Full Set Gradient ApproximationCode1
Pix4Point: Image Pretrained Standard Transformers for 3D Point Cloud UnderstandingCode1
Beyond single receptive field: A receptive field fusion-and-stratification network for airborne laser scanning point cloud classificationCode1
PointNorm: Dual Normalization is All You Need for Point Cloud AnalysisCode1
APP-Net: Auxiliary-point-based Push and Pull Operations for Efficient Point Cloud ClassificationCode1
Robust Structured Declarative Classifiers for 3D Point Clouds: Defending Adversarial Attacks with Implicit GradientsCode1
No Pain, Big Gain: Classify Dynamic Point Cloud Sequences with Static Models by Fitting Feature-level Space-time SurfacesCode1
Visualizing Global Explanations of Point Cloud DNNsCode1
Quasi-Balanced Self-Training on Noise-Aware Synthesis of Object Point Clouds for Closing Domain GapCode1
3DCTN: 3D Convolution-Transformer Network for Point Cloud ClassificationCode1
LPF-Defense: 3D Adversarial Defense based on Frequency AnalysisCode1
Benchmarking and Analyzing Point Cloud Classification under CorruptionsCode1
Learnable Lookup Table for Neural Network QuantizationCode1
Why Discard if You Can Recycle?: A Recycling Max Pooling Module for 3D Point Cloud AnalysisCode1
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point ModelingCode1
DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point CloudsCode1
ASSANet: An Anisotropic Separable Set Abstraction for Efficient Point Cloud Representation LearningCode1
Show:102550
← PrevPage 2 of 11Next →
All datasetsPointCloud-CISPRS

Benchmark Results

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