Shape Representation Of 3D Point Clouds on ModelNet40 10-way (10-shot)

Metric: Overall Accuracy (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	Overall Accuracy▼	Extra Data	Paper	Date↕	Code
1	Point-JEPA	95	Yes	Point-JEPA: A Joint Embedding Predictive Archite...	2024-04-25	Code
2	ReCon++	94.5	Yes	ShapeLLM: Universal 3D Object Understanding for ...	2024-02-27	Code
3	PointGPT	94.3	Yes	PointGPT: Auto-regressively Generative Pre-train...	2023-05-19	Code
4	3D-JEPA	94.3	Yes	3D-JEPA: A Joint Embedding Predictive Architectu...	2024-09-24	-
5	Point-FEMAE	94	Yes	Towards Compact 3D Representations via Point Fea...	2023-12-17	Code
6	point2vec	93.9	Yes	Point2Vec for Self-Supervised Representation Lea...	2023-03-29	Code
7	PCP-MAE	93.5	No	PCP-MAE: Learning to Predict Centers for Point M...	2024-08-16	Code
8	ReCon	93.3	Yes	Contrast with Reconstruct: Contrastive 3D Repres...	2023-02-05	Code
9	ACT	93.3	Yes	Autoencoders as Cross-Modal Teachers: Can Pretra...	2022-12-16	Code
10	Point-RAE	93.3	Yes	Regress Before Construct: Regress Autoencoder fo...	2023-09-25	Code
11	OTMae3D	93.2	Yes	-	-	Code
12	IDPT	92.8	No	Instance-aware Dynamic Prompt Tuning for Pre-tra...	2023-04-14	Code
13	Point-MAE	92.6	Yes	Masked Autoencoders for Point Cloud Self-supervi...	2022-03-13	Code
14	Point-LGMask	92.6	Yes	-	-	Code
15	I2P-MAE	92.6	Yes	Learning 3D Representations from 2D Pre-trained ...	2022-12-13	Code
16	Point-M2AE	92.3	Yes	Point-M2AE: Multi-scale Masked Autoencoders for ...	2022-05-28	Code
17	MaskPoint	91.4	Yes	Masked Discrimination for Self-Supervised Learni...	2022-03-21	Code
18	Point-BERT	91	Yes	Point-BERT: Pre-training 3D Point Cloud Transfor...	2021-11-29	Code
19	CrossMoCo	88.7	No	-	-	Code
20	OcCo+PointNet	83.9	No	Unsupervised Point Cloud Pre-Training via Occlus...	2020-10-02	Code
21	OcCo+DGCNN	82.9	No	Unsupervised Point Cloud Pre-Training via Occlus...	2020-10-02	Code
22	GPr-Net + Hyp (512)	71.6	No	GPr-Net: Geometric Prototypical Network for Poin...	2023-04-12	Code
23	GPr-Net + Hyp (1024)	70.4	No	GPr-Net: Geometric Prototypical Network for Poin...	2023-04-12	Code
24	GPr-Net + Euc (512)	62.3	No	GPr-Net: Geometric Prototypical Network for Poin...	2023-04-12	Code
25	GPr-Net + Euc (1024)	62.1	No	GPr-Net: Geometric Prototypical Network for Poin...	2023-04-12	Code
26	SSFSL+PointNet	49.15	No	Self-Supervised Few-Shot Learning on Point Clouds	2020-09-29	Code
27	SSFSL+DGCNN	48.5	No	Self-Supervised Few-Shot Learning on Point Clouds	2020-09-29	Code
28	PointCNN	46.6	No	-	-	Code
29	PointNet	46.6	No	PointNet: Deep Learning on Point Sets for 3D Cla...	2016-12-02	Code
30	PointNet++	23.05	No	PointNet++: Deep Hierarchical Feature Learning o...	2017-06-07	Code
31	DGCNN	19.85	No	Dynamic Graph CNN for Learning on Point Clouds	2018-01-24	Code

#1Point-JEPASOTA
95
Overall Accuracy· Extra Data· 2024-04-25
Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud Code
#2ReCon++SOTA
94.5
Overall Accuracy· Extra Data· 2024-02-27
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction Code
#3PointGPTSOTA
94.3
Overall Accuracy· Extra Data· 2023-05-19
PointGPT: Auto-regressively Generative Pre-training from Point Clouds Code
#43D-JEPA
94.3
Overall Accuracy· Extra Data· 2024-09-24
3D-JEPA: A Joint Embedding Predictive Architecture for 3D Self-Supervised Representation Learning
#5Point-FEMAE
94
Overall Accuracy· Extra Data· 2023-12-17
Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoders Code
#6point2vecSOTA
93.9
Overall Accuracy· Extra Data· 2023-03-29
Point2Vec for Self-Supervised Representation Learning on Point Clouds Code
#7PCP-MAE
93.5
Overall Accuracy· 2024-08-16
PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders Code
#8ReCon
93.3
Overall Accuracy· Extra Data· 2023-02-05
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining Code
#9ACTSOTA
93.3
Overall Accuracy· Extra Data· 2022-12-16
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?Code
#10Point-RAE
93.3
Overall Accuracy· Extra Data· 2023-09-25
Regress Before Construct: Regress Autoencoder for Point Cloud Self-supervised Learning Code
#11OTMae3D
93.2
Overall Accuracy· Extra Data
No paperCode
#12IDPT
92.8
Overall Accuracy· 2023-04-14
Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models Code
#13Point-MAESOTA
92.6
Overall Accuracy· Extra Data· 2022-03-13
Masked Autoencoders for Point Cloud Self-supervised Learning Code
#14Point-LGMask
92.6
Overall Accuracy· Extra Data
No paperCode
#15I2P-MAE
92.6
Overall Accuracy· Extra Data· 2022-12-13
Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoders Code
#16Point-M2AE
92.3
Overall Accuracy· Extra Data· 2022-05-28
Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training Code
#17MaskPoint
91.4
Overall Accuracy· Extra Data· 2022-03-21
Masked Discrimination for Self-Supervised Learning on Point Clouds Code
#18Point-BERTSOTA
91
Overall Accuracy· Extra Data· 2021-11-29
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling Code
#19CrossMoCo
88.7
Overall Accuracy
No paperCode
#20OcCo+PointNetSOTA
83.9
Overall Accuracy· 2020-10-02
Unsupervised Point Cloud Pre-Training via Occlusion Completion Code
#21OcCo+DGCNN
82.9
Overall Accuracy· 2020-10-02
Unsupervised Point Cloud Pre-Training via Occlusion Completion Code
#22GPr-Net + Hyp (512)
71.6
Overall Accuracy· 2023-04-12
GPr-Net: Geometric Prototypical Network for Point Cloud Few-Shot Learning Code
#23GPr-Net + Hyp (1024)
70.4
Overall Accuracy· 2023-04-12
GPr-Net: Geometric Prototypical Network for Point Cloud Few-Shot Learning Code
#24GPr-Net + Euc (512)
62.3
Overall Accuracy· 2023-04-12
GPr-Net: Geometric Prototypical Network for Point Cloud Few-Shot Learning Code
#25GPr-Net + Euc (1024)
62.1
Overall Accuracy· 2023-04-12
GPr-Net: Geometric Prototypical Network for Point Cloud Few-Shot Learning Code
#26SSFSL+PointNetSOTA
49.15
Overall Accuracy· 2020-09-29
Self-Supervised Few-Shot Learning on Point Clouds Code
#27SSFSL+DGCNN
48.5
Overall Accuracy· 2020-09-29
Self-Supervised Few-Shot Learning on Point Clouds Code
#28PointCNN
46.6
Overall Accuracy
No paperCode
#29PointNetSOTA
46.6
Overall Accuracy· 2016-12-02
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation Code
#30PointNet++
23.05
Overall Accuracy· 2017-06-07
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space Code
#31DGCNN
19.85
Overall Accuracy· 2018-01-24
Dynamic Graph CNN for Learning on Point Clouds Code