Shape Representation Of 3D Point Clouds on ModelNet40 5-way (20-shot)

Metric: Standard Deviation (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	Standard Deviation▼	Extra Data	Paper	Date↕	Code
1	PointNet	15.5	No	PointNet: Deep Learning on Point Sets for 3D Cla...	2016-12-02	Code
2	DGCNN	14.6	No	Dynamic Graph CNN for Learning on Point Clouds	2018-01-24	Code
3	PointNet++	14.2	No	PointNet++: Deep Hierarchical Feature Learning o...	2017-06-07	Code
4	SSFSL+PointNet	9.4	No	Self-Supervised Few-Shot Learning on Point Clouds	2020-09-29	Code
5	SSFSL+DGCNN	8.4	No	Self-Supervised Few-Shot Learning on Point Clouds	2020-09-29	Code
6	PointCNN	7	No	-	-	Code
7	Point-BERT	2.7	Yes	Point-BERT: Pre-training 3D Point Cloud Transfor...	2021-11-29	Code
8	GPr-Net + Euc (512)	2.4	No	GPr-Net: Geometric Prototypical Network for Poin...	2023-04-12	Code
9	GPr-Net + Euc (1024)	2.1	No	GPr-Net: Geometric Prototypical Network for Poin...	2023-04-12	Code
10	OcCo+DGCNN	1.9	No	Unsupervised Point Cloud Pre-Training via Occlus...	2020-10-02	Code
11	Point-MAE	1.8	Yes	Masked Autoencoders for Point Cloud Self-supervi...	2022-03-13	Code
12	MaskPoint	1.7	Yes	Masked Discrimination for Self-Supervised Learni...	2022-03-21	Code
13	CrossMoCo	1.7	No	-	-	Code
14	OcCo+PointNet	1.6	No	Unsupervised Point Cloud Pre-Training via Occlus...	2020-10-02	Code
15	Point-M2AE	1.4	Yes	Point-M2AE: Multi-scale Masked Autoencoders for ...	2022-05-28	Code
16	Point-LGMask	1.4	Yes	-	-	Code
17	ACT	1.4	Yes	Autoencoders as Cross-Modal Teachers: Can Pretra...	2022-12-16	Code
18	Point-RAE	1.3	Yes	Regress Before Construct: Regress Autoencoder fo...	2023-09-25	Code
19	I2P-MAE	1.3	Yes	Learning 3D Representations from 2D Pre-trained ...	2022-12-13	Code
20	GPr-Net + Hyp (512)	1.3	No	GPr-Net: Geometric Prototypical Network for Poin...	2023-04-12	Code
21	ReCon	1.2	Yes	Contrast with Reconstruct: Contrastive 3D Repres...	2023-02-05	Code
22	point2vec	1.2	Yes	Point2Vec for Self-Supervised Representation Lea...	2023-03-29	Code
23	OTMae3D	1.2	Yes	-	-	Code
24	PointGPT	1	Yes	PointGPT: Auto-regressively Generative Pre-train...	2023-05-19	Code
25	GPr-Net + Hyp (1024)	0.9	No	GPr-Net: Geometric Prototypical Network for Poin...	2023-04-12	Code
26	ReCon++	0.8	Yes	ShapeLLM: Universal 3D Object Understanding for ...	2024-02-27	Code
27	Point-JEPA	0.8	Yes	Point-JEPA: A Joint Embedding Predictive Archite...	2024-04-25	Code
28	PCP-MAE	0.8	No	PCP-MAE: Learning to Predict Centers for Point M...	2024-08-16	Code
29	3D-JEPA	0.4	Yes	3D-JEPA: A Joint Embedding Predictive Architectu...	2024-09-24	-

#1PointNetSOTA
15.5
Standard Deviation· 2016-12-02
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation Code
#2DGCNN
14.6
Standard Deviation· 2018-01-24
Dynamic Graph CNN for Learning on Point Clouds Code
#3PointNet++
14.2
Standard Deviation· 2017-06-07
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space Code
#4SSFSL+PointNet
9.4
Standard Deviation· 2020-09-29
Self-Supervised Few-Shot Learning on Point Clouds Code
#5SSFSL+DGCNN
8.4
Standard Deviation· 2020-09-29
Self-Supervised Few-Shot Learning on Point Clouds Code
#6PointCNN
7
Standard Deviation
No paperCode
#7Point-BERT
2.7
Standard Deviation· Extra Data· 2021-11-29
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling Code
#8GPr-Net + Euc (512)
2.4
Standard Deviation· 2023-04-12
GPr-Net: Geometric Prototypical Network for Point Cloud Few-Shot Learning Code
#9GPr-Net + Euc (1024)
2.1
Standard Deviation· 2023-04-12
GPr-Net: Geometric Prototypical Network for Point Cloud Few-Shot Learning Code
#10OcCo+DGCNN
1.9
Standard Deviation· 2020-10-02
Unsupervised Point Cloud Pre-Training via Occlusion Completion Code
#11Point-MAE
1.8
Standard Deviation· Extra Data· 2022-03-13
Masked Autoencoders for Point Cloud Self-supervised Learning Code
#12MaskPoint
1.7
Standard Deviation· Extra Data· 2022-03-21
Masked Discrimination for Self-Supervised Learning on Point Clouds Code
#13CrossMoCo
1.7
Standard Deviation
No paperCode
#14OcCo+PointNet
1.6
Standard Deviation· 2020-10-02
Unsupervised Point Cloud Pre-Training via Occlusion Completion Code
#15Point-M2AE
1.4
Standard Deviation· Extra Data· 2022-05-28
Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training Code
#16Point-LGMask
1.4
Standard Deviation· Extra Data
No paperCode
#17ACT
1.4
Standard Deviation· Extra Data· 2022-12-16
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?Code
#18Point-RAE
1.3
Standard Deviation· Extra Data· 2023-09-25
Regress Before Construct: Regress Autoencoder for Point Cloud Self-supervised Learning Code
#19I2P-MAE
1.3
Standard Deviation· Extra Data· 2022-12-13
Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoders Code
#20GPr-Net + Hyp (512)
1.3
Standard Deviation· 2023-04-12
GPr-Net: Geometric Prototypical Network for Point Cloud Few-Shot Learning Code
#21ReCon
1.2
Standard Deviation· Extra Data· 2023-02-05
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining Code
#22point2vec
1.2
Standard Deviation· Extra Data· 2023-03-29
Point2Vec for Self-Supervised Representation Learning on Point Clouds Code
#23OTMae3D
1.2
Standard Deviation· Extra Data
No paperCode
#24PointGPT
1
Standard Deviation· Extra Data· 2023-05-19
PointGPT: Auto-regressively Generative Pre-training from Point Clouds Code
#25GPr-Net + Hyp (1024)
0.9
Standard Deviation· 2023-04-12
GPr-Net: Geometric Prototypical Network for Point Cloud Few-Shot Learning Code
#26ReCon++
0.8
Standard Deviation· Extra Data· 2024-02-27
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction Code
#27Point-JEPA
0.8
Standard Deviation· Extra Data· 2024-04-25
Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud Code
#28PCP-MAE
0.8
Standard Deviation· 2024-08-16
PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders Code
#293D-JEPA
0.4
Standard Deviation· Extra Data· 2024-09-24
3D-JEPA: A Joint Embedding Predictive Architecture for 3D Self-Supervised Representation Learning