SOTAVerified|Agents Browse Leaderboard About

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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 11–20 of 21 papers

Title	Date	Tasks	Status	Hype	Score
Self-supervised Learning of Point Clouds via Orientation Estimation	Aug 1, 2020	3D Point Cloud Linear ClassificationSelf-Supervised Learning	CodeCode Available	1	5
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining	Feb 5, 2023	3D Point Cloud Classification3D Point Cloud Linear Classification	CodeCode Available	1	5
AdaCrossNet: Adaptive Dynamic Loss Weighting for Cross-Modal Contrastive Point Cloud Learning	Jan 2, 2025	3D Part Segmentation3D Point Cloud Classification	CodeCode Available	0	5
CrossMoCo: Multi-modal Momentum Contrastive Learning for Point Cloud	Jun 8, 2023	3D Object Classification3D Point Cloud Classification	CodeCode Available	0	5
FoldingNet: Point Cloud Auto-encoder via Deep Grid Deformation	Dec 19, 2017	3D Point Cloud Linear ClassificationDecoder	CodeCode Available	0	5
Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling	Oct 24, 2016	3D Object Recognition3D Point Cloud Linear Classification	CodeCode Available	0	5
SO-Net: Self-Organizing Network for Point Cloud Analysis	Mar 12, 2018	3D Part Segmentation3D Point Cloud Classification	CodeCode Available	0	5
View Inter-Prediction GAN: Unsupervised Representation Learning for 3D Shapes by Learning Global Shape Memories to Support Local View Predictions	Nov 7, 2018	3D Point Cloud Linear ClassificationPrediction	—Unverified	0	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	Jul 30, 2019	3D Point Cloud Linear ClassificationUnsupervised 3D Point Cloud Linear Evaluation	—Unverified	0	0
Self-Supervised Deep Learning on Point Clouds by Reconstructing Space	Jan 24, 2019	3D Point Cloud Linear ClassificationDeep Learning	—Unverified	0	0

Show:10 25 50

← PrevPage 2 of 3Next →

All datasets ModelNet40 ScanObjectNN

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	I2P-MAE	Overall Accuracy	93.4	—	Unverified
2	IAE (DGCNN)	Overall Accuracy	92.1	—	Unverified
3	AdaCrossNet	Overall Accuracy	91.8	—	Unverified
4	CrossMoCo	Overall Accuracy	91.49	—	Unverified
5	CrossPoint	Overall Accuracy	91.2	—	Unverified
6	STRL	Overall Accuracy	90.9	—	Unverified
7	PSG-Net	Overall Accuracy	90.9	—	Unverified
8	PointOE	Overall Accuracy	90.7	—	Unverified
9	Point-Jigsaw	Overall Accuracy	90.6	—	Unverified
10	MID-FC	Overall Accuracy	90.3	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	CrossMoCo	Overall Accuracy	86.06	—	Unverified
2	AdaCrossNet	Overall Accuracy	82.1	—	Unverified
3	CrossPoint	Overall Accuracy	81.7	—	Unverified
4	OcCo	Overall Accuracy	78.3	—	Unverified