SOTAVerified

3D Point Cloud Classification

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–100 of 202 papers

TitleStatusHype
Evaluating Machine Learning Models with NERO: Non-Equivariance Revealed on Orbits—0
GTNet: Graph Transformer Network for 3D Point Cloud Classification and Semantic Segmentation—0
Connecting Multi-modal Contrastive Representations—0
PointGPT: Auto-regressively Generative Pre-training from Point CloudsCode2
SUG: Single-dataset Unified Generalization for 3D Point Cloud ClassificationCode1
ULIP-2: Towards Scalable Multimodal Pre-training for 3D UnderstandingCode2
Multi-view Vision-Prompt Fusion Network: Can 2D Pre-trained Model Boost 3D Point Cloud Data-scarce Learning?—0
Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud ModelsCode1
Multi-scale Geometry-aware Transformer for 3D Point Cloud Classification—0
A Closer Look at Few-Shot 3D Point Cloud ClassificationCode1
Point2Vec for Self-Supervised Representation Learning on Point CloudsCode1
Self-positioning Point-based Transformer for Point Cloud UnderstandingCode1
Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud AnalysisCode2
Interpreting Hidden Semantics in the Intermediate Layers of 3D Point Cloud Classification Neural Network—0
Point Cloud Classification Using Content-based Transformer via Clustering in Feature SpaceCode1
Attention-based Point Cloud Edge SamplingCode1
CLR-GAM: Contrastive Point Cloud Learning with Guided Augmentation and Feature Mapping—0
S3I-PointHop: SO(3)-Invariant PointHop for 3D Point Cloud Classification—0
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative PretrainingCode1
Improved Training for 3D Point Cloud ClassificationCode0
Computation and Data Efficient Backdoor Attacks—0
FFF: Fragment-Guided Flexible Fitting for Building Complete Protein Structures—0
CAP: Robust Point Cloud Classification via Semantic and Structural Modeling—0
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?Code1
Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked AutoencodersCode2
ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D UnderstandingCode2
TetraSphere: A Neural Descriptor for O(3)-Invariant Point Cloud AnalysisCode1
Text2Model: Text-based Model Induction for Zero-shot Image Classification—0
LCPFormer: Towards Effective 3D Point Cloud Analysis via Local Context Propagation in TransformersCode0
Understanding Key Point Cloud Features for Development Three-dimensional Adversarial Attacks—0
SageMix: Saliency-Guided Mixup for Point CloudsCode1
Point Transformer V2: Grouped Vector Attention and Partition-based PoolingCode2
APSNet: Attention Based Point Cloud SamplingCode1
Let Images Give You More:Point Cloud Cross-Modal Training for Shape AnalysisCode2
CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-trainingCode1
Automated Mobile Attention KPConv Networks via a Wide and Deep Predictor—0
A Simple Strategy to Provable Invariance via Orbit Mapping—0
Rethinking the compositionality of point clouds through regularization in the hyperbolic spaceCode1
SimpleView++: Neighborhood Views for Point Cloud ClassificationCode0
Pix4Point: Image Pretrained Standard Transformers for 3D Point Cloud UnderstandingCode1
Quantifying the Knowledge in a DNN to Explain Knowledge Distillation for Classification—0
P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel PromptingCode1
PointNeXt: Revisiting PointNet++ with Improved Training and Scaling StrategiesCode3
Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-trainingCode2
PointVector: A Vector Representation In Point Cloud AnalysisCode0
Advanced Feature Learning on Point Clouds using Multi-resolution Features and Learnable PoolingCode1
Surface Representation for Point CloudsCode2
APP-Net: Auxiliary-point-based Push and Pull Operations for Efficient Point Cloud ClassificationCode1
Open-Set Semi-Supervised Learning for 3D Point Cloud Understanding—0
Points to Patches: Enabling the Use of Self-Attention for 3D Shape RecognitionCode1
Show:102550
← PrevPage 2 of 5Next →
All datasetsModelNet40ScanObjectNNModelNet40-CIntrASydney Urban Objects

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1PointGSTOverall Accuracy95.3—Unverified
2Mamba3D + Point-MAEOverall Accuracy95.1—Unverified
3ReCon++Overall Accuracy95—Unverified
4PointGPTOverall Accuracy94.9—Unverified
5point2vecOverall Accuracy94.8—Unverified
6RepSurf-UOverall Accuracy94.7—Unverified
7ReConOverall Accuracy94.7—Unverified
8ULIP + PointMLPOverall Accuracy94.7—Unverified
9AsymDSD-B* (no voting)Overall Accuracy94.7—Unverified
10PointMLP+HyCoReOverall Accuracy94.5—Unverified
#ModelMetricClaimedVerifiedStatus
1OmniVec2Overall Accuracy97.2—Unverified
2PointGSTOverall Accuracy96.18—Unverified
3OmniVecOverall Accuracy96.1—Unverified
4GPSFormerOverall Accuracy95.4—Unverified
5ReCon++Overall Accuracy95.25—Unverified
6AsymDSD-B* (no voting)Overall Accuracy93.72—Unverified
7PointGPTOverall Accuracy93.4—Unverified
8GPSFormer-eliteOverall Accuracy93.3—Unverified
9Mamba3DOverall Accuracy92.64—Unverified
10Mamba3D (no voting)Overall Accuracy91.81—Unverified
#ModelMetricClaimedVerifiedStatus
1PointNetError Rate0.28—Unverified
2SimpleViewError Rate0.27—Unverified
3RSCNNError Rate0.26—Unverified
4DGCNNError Rate0.26—Unverified
5PCTError Rate0.26—Unverified
6PointNet++Error Rate0.24—Unverified
7PointNet++/+PointMixupError Rate0.19—Unverified
8PointNet++/+PointCutMix-RError Rate0.19—Unverified
9PCT+RSMixError Rate0.17—Unverified
10DGCNN+PointCutMix-RError Rate0.17—Unverified