3D Point Cloud Classification on ModelNet40 10-way (20-shot)

Metric: Overall Accuracy (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	Overall Accuracy▼	Extra Data	Paper	Date↕	Code
1	ReCon++	96.5	Yes	ShapeLLM: Universal 3D Object Understanding for ...	2024-02-27	Code
2	Point-JEPA	96.4	Yes	Point-JEPA: A Joint Embedding Predictive Archite...	2024-04-25	Code
3	3D-JEPA	96.3	Yes	3D-JEPA: A Joint Embedding Predictive Architectu...	2024-09-24	-
4	PointGPT	96.1	Yes	PointGPT: Auto-regressively Generative Pre-train...	2023-05-19	Code
5	PCP-MAE	95.9	No	PCP-MAE: Learning to Predict Centers for Point M...	2024-08-16	Code
6	ReCon	95.8	Yes	Contrast with Reconstruct: Contrastive 3D Repres...	2023-02-05	Code
7	Point-RAE	95.8	Yes	Regress Before Construct: Regress Autoencoder fo...	2023-09-25	Code
8	point2vec	95.8	Yes	Point2Vec for Self-Supervised Representation Lea...	2023-03-29	Code
9	Point-FEMAE	95.8	Yes	Towards Compact 3D Representations via Point Fea...	2023-12-17	Code
10	OTMae3D	95.6	Yes	-	-	Code
11	ACT	95.6	Yes	Autoencoders as Cross-Modal Teachers: Can Pretra...	2022-12-16	Code
12	I2P-MAE	95.5	Yes	Learning 3D Representations from 2D Pre-trained ...	2022-12-13	Code
13	IDPT	95.4	No	Instance-aware Dynamic Prompt Tuning for Pre-tra...	2023-04-14	Code
14	Point-LGMask	95.1	Yes	-	-	Code
15	Point-M2AE	95	Yes	Point-M2AE: Multi-scale Masked Autoencoders for ...	2022-05-28	Code
16	Point-MAE	95	Yes	Masked Autoencoders for Point Cloud Self-supervi...	2022-03-13	Code
17	MaskPoint	93.4	Yes	Masked Discrimination for Self-Supervised Learni...	2022-03-21	Code
18	Point-BERT	92.7	Yes	Point-BERT: Pre-training 3D Point Cloud Transfor...	2021-11-29	Code
19	CrossMoCo	91	No	-	-	Code
20	OcCo+PointNet	89.7	No	Unsupervised Point Cloud Pre-Training via Occlus...	2020-10-02	Code
21	OcCo+DGCNN	86.5	No	Unsupervised Point Cloud Pre-Training via Occlus...	2020-10-02	Code
22	GPr-Net + Hyp (512)	73.8	No	GPr-Net: Geometric Prototypical Network for Poin...	2023-04-12	Code
23	GPr-Net + Hyp (1024)	72.8	No	GPr-Net: Geometric Prototypical Network for Poin...	2023-04-12	Code
24	GPr-Net + Euc (1024)	63.4	No	GPr-Net: Geometric Prototypical Network for Poin...	2023-04-12	Code
25	GPr-Net + Euc (512)	63.3	No	GPr-Net: Geometric Prototypical Network for Poin...	2023-04-12	Code
26	SSFSL+ DGCNN	53	No	Self-Supervised Few-Shot Learning on Point Clouds	2020-09-29	Code
27	SSFSL+PointNet	50.1	No	Self-Supervised Few-Shot Learning on Point Clouds	2020-09-29	Code
28	PointCNN	49.95	No	-	-	Code
29	PointNet	35.2	No	PointNet: Deep Learning on Point Sets for 3D Cla...	2016-12-02	Code
30	PointNet++	18.8	No	PointNet++: Deep Hierarchical Feature Learning o...	2017-06-07	Code
31	DGCNN	16.9	No	Dynamic Graph CNN for Learning on Point Clouds	2018-01-24	Code

#1ReCon++SOTA
96.5
Overall Accuracy· Extra Data· 2024-02-27
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction Code
#2Point-JEPA
96.4
Overall Accuracy· Extra Data· 2024-04-25
Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud Code
#33D-JEPA
96.3
Overall Accuracy· Extra Data· 2024-09-24
3D-JEPA: A Joint Embedding Predictive Architecture for 3D Self-Supervised Representation Learning
#4PointGPTSOTA
96.1
Overall Accuracy· Extra Data· 2023-05-19
PointGPT: Auto-regressively Generative Pre-training from Point Clouds Code
#5PCP-MAE
95.9
Overall Accuracy· 2024-08-16
PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders Code
#6ReConSOTA
95.8
Overall Accuracy· Extra Data· 2023-02-05
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining Code
#7Point-RAE
95.8
Overall Accuracy· Extra Data· 2023-09-25
Regress Before Construct: Regress Autoencoder for Point Cloud Self-supervised Learning Code
#8point2vec
95.8
Overall Accuracy· Extra Data· 2023-03-29
Point2Vec for Self-Supervised Representation Learning on Point Clouds Code
#9Point-FEMAE
95.8
Overall Accuracy· Extra Data· 2023-12-17
Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoders Code
#10OTMae3D
95.6
Overall Accuracy· Extra Data
No paperCode
#11ACTSOTA
95.6
Overall Accuracy· Extra Data· 2022-12-16
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?Code
#12I2P-MAESOTA
95.5
Overall Accuracy· Extra Data· 2022-12-13
Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoders Code
#13IDPT
95.4
Overall Accuracy· 2023-04-14
Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models Code
#14Point-LGMask
95.1
Overall Accuracy· Extra Data
No paperCode
#15Point-M2AE
95
Overall Accuracy· Extra Data· 2022-05-28
Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training Code
#16Point-MAESOTA
95
Overall Accuracy· Extra Data· 2022-03-13
Masked Autoencoders for Point Cloud Self-supervised Learning Code
#17MaskPoint
93.4
Overall Accuracy· Extra Data· 2022-03-21
Masked Discrimination for Self-Supervised Learning on Point Clouds Code
#18Point-BERTSOTA
92.7
Overall Accuracy· Extra Data· 2021-11-29
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling Code
#19CrossMoCo
91
Overall Accuracy
No paperCode
#20OcCo+PointNetSOTA
89.7
Overall Accuracy· 2020-10-02
Unsupervised Point Cloud Pre-Training via Occlusion Completion Code
#21OcCo+DGCNN
86.5
Overall Accuracy· 2020-10-02
Unsupervised Point Cloud Pre-Training via Occlusion Completion Code
#22GPr-Net + Hyp (512)
73.8
Overall Accuracy· 2023-04-12
GPr-Net: Geometric Prototypical Network for Point Cloud Few-Shot Learning Code
#23GPr-Net + Hyp (1024)
72.8
Overall Accuracy· 2023-04-12
GPr-Net: Geometric Prototypical Network for Point Cloud Few-Shot Learning Code
#24GPr-Net + Euc (1024)
63.4
Overall Accuracy· 2023-04-12
GPr-Net: Geometric Prototypical Network for Point Cloud Few-Shot Learning Code
#25GPr-Net + Euc (512)
63.3
Overall Accuracy· 2023-04-12
GPr-Net: Geometric Prototypical Network for Point Cloud Few-Shot Learning Code
#26SSFSL+ DGCNNSOTA
53
Overall Accuracy· 2020-09-29
Self-Supervised Few-Shot Learning on Point Clouds Code
#27SSFSL+PointNet
50.1
Overall Accuracy· 2020-09-29
Self-Supervised Few-Shot Learning on Point Clouds Code
#28PointCNN
49.95
Overall Accuracy
No paperCode
#29PointNetSOTA
35.2
Overall Accuracy· 2016-12-02
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation Code
#30PointNet++
18.8
Overall Accuracy· 2017-06-07
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space Code
#31DGCNN
16.9
Overall Accuracy· 2018-01-24
Dynamic Graph CNN for Learning on Point Clouds Code