SOTAVerified

Point Cloud Classification

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

Papers

Showing 150 of 265 papers

TitleStatusHype
FRACTAL: An Ultra-Large-Scale Aerial Lidar Dataset for 3D Semantic Segmentation of Diverse LandscapesCode3
Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud LearningCode3
Point Transformer V2: Grouped Vector Attention and Partition-based PoolingCode2
Beyond Self-attention: External Attention using Two Linear Layers for Visual TasksCode2
Curvature Diversity-Driven Deformation and Domain Alignment for Point CloudCode2
Frozen Transformers in Language Models Are Effective Visual Encoder LayersCode2
PointHop: An Explainable Machine Learning Method for Point Cloud ClassificationCode1
Point-GN: A Non-Parametric Network Using Gaussian Positional Encoding for Point Cloud ClassificationCode1
PointMixup: Augmentation for Point CloudsCode1
PointAugment: an Auto-Augmentation Framework for Point Cloud ClassificationCode1
Self-supervised Point Cloud Representation Learning via Separating Mixed ShapesCode1
PointCutMix: Regularization Strategy for Point Cloud ClassificationCode1
Geometry-Aware Self-Training for Unsupervised Domain Adaptationon Object Point CloudsCode1
PointHop++: A Lightweight Learning Model on Point Sets for 3D ClassificationCode1
No Pain, Big Gain: Classify Dynamic Point Cloud Sequences with Static Models by Fitting Feature-level Space-time SurfacesCode1
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point ModelingCode1
LPF-Defense: 3D Adversarial Defense based on Frequency AnalysisCode1
Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point CloudCode1
Differentiable Euler Characteristic Transforms for Shape ClassificationCode1
MOPS-Net: A Matrix Optimization-driven Network forTask-Oriented 3D Point Cloud DownsamplingCode1
Dynamic Graph CNN for Learning on Point CloudsCode1
Pix4Point: Image Pretrained Standard Transformers for 3D Point Cloud UnderstandingCode1
Geometry-Aware Self-Training for Unsupervised Domain Adaptation on Object Point CloudsCode1
Point Cloud Classification Using Content-based Transformer via Clustering in Feature SpaceCode1
MATE: Masked Autoencoders are Online 3D Test-Time LearnersCode1
Exploiting Inductive Bias in Transformer for Point Cloud Classification and SegmentationCode1
A Closer Look at Few-Shot 3D Point Cloud ClassificationCode1
Generative PointNet: Deep Energy-Based Learning on Unordered Point Sets for 3D Generation, Reconstruction and ClassificationCode1
ASSANet: An Anisotropic Separable Set Abstraction for Efficient Point Cloud Representation LearningCode1
APP-Net: Auxiliary-point-based Push and Pull Operations for Efficient Point Cloud ClassificationCode1
Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point CloudsCode1
DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point CloudsCode1
Image2Point: 3D Point-Cloud Understanding with 2D Image Pretrained ModelsCode1
Collect-and-Distribute Transformer for 3D Point Cloud AnalysisCode1
Deep Declarative Networks: A New HopeCode1
Learnable Lookup Table for Neural Network QuantizationCode1
Benchmarking and Analyzing Point Cloud Classification under CorruptionsCode1
Deep SetsCode1
APSNet: Attention Based Point Cloud SamplingCode1
Beyond single receptive field: A receptive field fusion-and-stratification network for airborne laser scanning point cloud classificationCode1
Dense-Resolution Network for Point Cloud Classification and SegmentationCode1
Dynamic Local Feature Aggregation for Learning on Point CloudsCode1
Implicit Convolutional Kernels for Steerable CNNsCode1
PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point CloudsCode1
PCT: Point cloud transformerCode1
Parameter-Efficient Person Re-identification in the 3D SpaceCode1
3DCTN: 3D Convolution-Transformer Network for Point Cloud ClassificationCode1
ModelNet-O: A Large-Scale Synthetic Dataset for Occlusion-Aware Point Cloud ClassificationCode1
CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-trainingCode1
Point Cloud Augmentation with Weighted Local TransformationsCode1
Show:102550
← PrevPage 1 of 6Next →

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