SOTAVerified

3D Point Cloud Classification

Papers

Showing 150 of 202 papers

TitleStatusHype
PointNeXt: Revisiting PointNet++ with Improved Training and Scaling StrategiesCode3
ShapeLLM: Universal 3D Object Understanding for Embodied InteractionCode3
Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud LearningCode3
PointCNN: Convolution On X-Transformed PointsCode3
FRACTAL: An Ultra-Large-Scale Aerial Lidar Dataset for 3D Semantic Segmentation of Diverse LandscapesCode3
PCP-MAE: Learning to Predict Centers for Point Masked AutoencodersCode2
Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud AnalysisCode2
KPConvX: Modernizing Kernel Point Convolution with Kernel AttentionCode2
Surface Representation for Point CloudsCode2
ULIP-2: Towards Scalable Multimodal Pre-training for 3D UnderstandingCode2
Let Images Give You More:Point Cloud Cross-Modal Training for Shape AnalysisCode2
Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-trainingCode2
Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space ModelCode2
Point Transformer V2: Grouped Vector Attention and Partition-based PoolingCode2
PointGPT: Auto-regressively Generative Pre-training from Point CloudsCode2
Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP FrameworkCode2
ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D UnderstandingCode2
Benchmarking Robustness of 3D Point Cloud Recognition Against Common CorruptionsCode2
Masked Autoencoders for Point Cloud Self-supervised LearningCode2
Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked AutoencodersCode2
DeepGCNs: Making GCNs Go as Deep as CNNsCode2
Perceiver: General Perception with Iterative AttentionCode1
Parameter-Efficient Person Re-identification in the 3D SpaceCode1
Advanced Feature Learning on Point Clouds using Multi-resolution Features and Learnable PoolingCode1
Beyond First Impressions: Integrating Joint Multi-modal Cues for Comprehensive 3D RepresentationCode1
P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel PromptingCode1
GPSFormer: A Global Perception and Local Structure Fitting-based Transformer for Point Cloud UnderstandingCode1
ExpPoint-MAE: Better interpretability and performance for self-supervised point cloud transformersCode1
CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-trainingCode1
PCT: Point cloud transformerCode1
MVTN: Multi-View Transformation Network for 3D Shape RecognitionCode1
PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point CloudsCode1
Pix4Point: Image Pretrained Standard Transformers for 3D Point Cloud UnderstandingCode1
LPF-Defense: 3D Adversarial Defense based on Frequency AnalysisCode1
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?Code1
Learning to SampleCode1
Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point CloudCode1
DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point CloudsCode1
Learning Inner-Group Relations on Point CloudsCode1
Decoupled Local Aggregation for Point Cloud LearningCode1
Dense-Resolution Network for Point Cloud Classification and SegmentationCode1
Attention-based Point Cloud Edge SamplingCode1
3D Medical Point Transformer: Introducing Convolution to Attention Networks for Medical Point Cloud AnalysisCode1
diffConv: Analyzing Irregular Point Clouds with an Irregular ViewCode1
DSPoint: Dual-scale Point Cloud Recognition with High-frequency FusionCode1
APSNet: Attention Based Point Cloud SamplingCode1
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative PretrainingCode1
3D ShapeNets: A Deep Representation for Volumetric ShapesCode1
Dynamic Graph CNN for Learning on Point CloudsCode1
Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud ModelsCode1
Show:102550
← PrevPage 1 of 5Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1PointGSTOverall Accuracy95.3Unverified
2Mamba3D + Point-MAEOverall Accuracy95.1Unverified
3ReCon++Overall Accuracy95Unverified
4PointGPTOverall Accuracy94.9Unverified
5point2vecOverall Accuracy94.8Unverified
6AsymDSD-B* (no voting)Overall Accuracy94.7Unverified
7ULIP + PointMLPOverall Accuracy94.7Unverified
8ReConOverall Accuracy94.7Unverified
9RepSurf-UOverall Accuracy94.7Unverified
10PointMLP+HyCoReOverall Accuracy94.5Unverified
#ModelMetricClaimedVerifiedStatus
1OmniVec2Overall Accuracy97.2Unverified
2PointGSTOverall Accuracy96.18Unverified
3OmniVecOverall Accuracy96.1Unverified
4GPSFormerOverall Accuracy95.4Unverified
5ReCon++Overall Accuracy95.25Unverified
6AsymDSD-B* (no voting)Overall Accuracy93.72Unverified
7PointGPTOverall Accuracy93.4Unverified
8GPSFormer-eliteOverall Accuracy93.3Unverified
9Mamba3DOverall Accuracy92.64Unverified
10Mamba3D (no voting)Overall Accuracy91.81Unverified
#ModelMetricClaimedVerifiedStatus
1PointNetError Rate0.28Unverified
2SimpleViewError Rate0.27Unverified
3RSCNNError Rate0.26Unverified
4DGCNNError Rate0.26Unverified
5PCTError Rate0.26Unverified
6PointNet++Error Rate0.24Unverified
7PointNet++/+PointMixupError Rate0.19Unverified
8PointNet++/+PointCutMix-RError Rate0.19Unverified
9DGCNN+PointCutMix-RError Rate0.17Unverified
10PCT+RSMixError Rate0.17Unverified