SOTAVerified

3D Point Cloud Linear Classification

Training a linear classifier(e.g. SVM) on the embeddings/representations of 3D point clouds. The embeddings/representations are usually trained in an unsupervised manner.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–21 of 21 papers

TitleStatusHype
ShapeLLM: Universal 3D Object Understanding for Embodied InteractionCode3
CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud UnderstandingCode2
Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked AutoencodersCode2
Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-trainingCode2
Spatio-temporal Self-Supervised Representation Learning for 3D Point CloudsCode1
Implicit Autoencoder for Point-Cloud Self-Supervised Representation LearningCode1
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative PretrainingCode1
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point ModelingCode1
Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point CloudCode1
Unsupervised Point Cloud Pre-Training via Occlusion CompletionCode1
Unsupervised 3D Learning for Shape Analysis via Multiresolution Instance DiscriminationCode1
Self-supervised Learning of Point Clouds via Orientation EstimationCode1
View Inter-Prediction GAN: Unsupervised Representation Learning for 3D Shapes by Learning Global Shape Memories to Support Local View Predictions—0
Self-Supervised Deep Learning on Point Clouds by Reconstructing Space—0
Multi-Angle Point Cloud-VAE: Unsupervised Feature Learning for 3D Point Clouds from Multiple Angles by Joint Self-Reconstruction and Half-to-Half Prediction—0
Progressive Seed Generation Auto-encoder for Unsupervised Point Cloud Learning—0
Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial ModelingCode0
SO-Net: Self-Organizing Network for Point Cloud AnalysisCode0
FoldingNet: Point Cloud Auto-encoder via Deep Grid DeformationCode0
CrossMoCo: Multi-modal Momentum Contrastive Learning for Point CloudCode0
AdaCrossNet: Adaptive Dynamic Loss Weighting for Cross-Modal Contrastive Point Cloud LearningCode0
Show:102550
All datasetsModelNet40ScanObjectNN

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1I2P-MAEOverall Accuracy93.4—Unverified
2IAE (DGCNN)Overall Accuracy92.1—Unverified
3AdaCrossNetOverall Accuracy91.8—Unverified
4CrossMoCoOverall Accuracy91.49—Unverified
5CrossPointOverall Accuracy91.2—Unverified
6STRLOverall Accuracy90.9—Unverified
7PSG-NetOverall Accuracy90.9—Unverified
8PointOEOverall Accuracy90.7—Unverified
9Point-JigsawOverall Accuracy90.6—Unverified
10MID-FCOverall Accuracy90.3—Unverified
#ModelMetricClaimedVerifiedStatus
1CrossMoCoOverall Accuracy86.06—Unverified
2AdaCrossNetOverall Accuracy82.1—Unverified
3CrossPointOverall Accuracy81.7—Unverified
4OcCoOverall Accuracy78.3—Unverified