3D Point Cloud Reconstruction on ModelNet40 5-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	PointGPT	98	Yes	PointGPT: Auto-regressively Generative Pre-train...	2023-05-19	Code
2	ReCon++	98	Yes	ShapeLLM: Universal 3D Object Understanding for ...	2024-02-27	Code
3	3D-JEPA	97.6	Yes	3D-JEPA: A Joint Embedding Predictive Architectu...	2024-09-24	-
4	Point-LGMask	97.4	Yes	-	-	Code
5	Point-JEPA	97.4	Yes	Point-JEPA: A Joint Embedding Predictive Archite...	2024-04-25	Code
6	PCP-MAE	97.4	No	PCP-MAE: Learning to Predict Centers for Point M...	2024-08-16	Code
7	Point-RAE	97.3	Yes	Regress Before Construct: Regress Autoencoder fo...	2023-09-25	Code
8	ReCon	97.3	Yes	Contrast with Reconstruct: Contrastive 3D Repres...	2023-02-05	Code
9	IDPT	97.3	No	Instance-aware Dynamic Prompt Tuning for Pre-tra...	2023-04-14	Code
10	OTMae3D	97.2	Yes	-	-	Code
11	I2P-MAE	97	Yes	Learning 3D Representations from 2D Pre-trained ...	2022-12-13	Code
12	point2vec	97	Yes	Point2Vec for Self-Supervised Representation Lea...	2023-03-29	Code
13	Point-M2AE	96.8	Yes	Point-M2AE: Multi-scale Masked Autoencoders for ...	2022-05-28	Code
14	ACT	96.8	Yes	Autoencoders as Cross-Modal Teachers: Can Pretra...	2022-12-16	Code
15	Point-MAE	96.3	Yes	Masked Autoencoders for Point Cloud Self-supervi...	2022-03-13	Code
16	MaskPoint	95	Yes	Masked Discrimination for Self-Supervised Learni...	2022-03-21	Code
17	Point-BERT	94.6	Yes	Point-BERT: Pre-training 3D Point Cloud Transfor...	2021-11-29	Code
18	CrossMoCo	93.8	No	-	-	Code
19	OcCo+DGCNN	90.6	No	Unsupervised Point Cloud Pre-Training via Occlus...	2020-10-02	Code
20	OcCo+PointNet	89.7	No	Unsupervised Point Cloud Pre-Training via Occlus...	2020-10-02	Code
21	GPr-Net + Hyp (512)	81.1	No	GPr-Net: Geometric Prototypical Network for Poin...	2023-04-12	Code
22	GPr-Net + Hyp (1024)	80.4	No	GPr-Net: Geometric Prototypical Network for Poin...	2023-04-12	Code
23	GPr-Net + Euc (1024)	74.4	No	GPr-Net: Geometric Prototypical Network for Poin...	2023-04-12	Code
24	GPr-Net + Euc (512)	74	No	GPr-Net: Geometric Prototypical Network for Poin...	2023-04-12	Code
25	PointCNN	65.41	No	PointCNN: Convolution On $\mathcal{X}$-Transform...	2018-01-23	Code
26	SSFSL+PointNet	63.2	No	Self-Supervised Few-Shot Learning on Point Clouds	2020-09-29	Code
27	SSFSL+DGCNN	60	No	Self-Supervised Few-Shot Learning on Point Clouds	2020-09-29	Code
28	PointNet	51.97	No	PointNet: Deep Learning on Point Sets for 3D Cla...	2016-12-02	Code
29	PointNet++	38.53	No	PointNet++: Deep Hierarchical Feature Learning o...	2017-06-07	Code
30	DGCNN	31.6	No	Dynamic Graph CNN for Learning on Point Clouds	2018-01-24	Code

#1PointGPTSOTA
98
Overall Accuracy· Extra Data· 2023-05-19
PointGPT: Auto-regressively Generative Pre-training from Point Clouds Code
#2ReCon++
98
Overall Accuracy· Extra Data· 2024-02-27
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction Code
#33D-JEPA
97.6
Overall Accuracy· Extra Data· 2024-09-24
3D-JEPA: A Joint Embedding Predictive Architecture for 3D Self-Supervised Representation Learning
#4Point-LGMask
97.4
Overall Accuracy· Extra Data
No paperCode
#5Point-JEPA
97.4
Overall Accuracy· Extra Data· 2024-04-25
Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud Code
#6PCP-MAE
97.4
Overall Accuracy· 2024-08-16
PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders Code
#7Point-RAE
97.3
Overall Accuracy· Extra Data· 2023-09-25
Regress Before Construct: Regress Autoencoder for Point Cloud Self-supervised Learning Code
#8ReConSOTA
97.3
Overall Accuracy· Extra Data· 2023-02-05
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining Code
#9IDPT
97.3
Overall Accuracy· 2023-04-14
Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models Code
#10OTMae3D
97.2
Overall Accuracy· Extra Data
No paperCode
#11I2P-MAESOTA
97
Overall Accuracy· Extra Data· 2022-12-13
Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoders Code
#12point2vec
97
Overall Accuracy· Extra Data· 2023-03-29
Point2Vec for Self-Supervised Representation Learning on Point Clouds Code
#13Point-M2AESOTA
96.8
Overall Accuracy· Extra Data· 2022-05-28
Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training Code
#14ACT
96.8
Overall Accuracy· Extra Data· 2022-12-16
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?Code
#15Point-MAESOTA
96.3
Overall Accuracy· Extra Data· 2022-03-13
Masked Autoencoders for Point Cloud Self-supervised Learning Code
#16MaskPoint
95
Overall Accuracy· Extra Data· 2022-03-21
Masked Discrimination for Self-Supervised Learning on Point Clouds Code
#17Point-BERTSOTA
94.6
Overall Accuracy· Extra Data· 2021-11-29
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling Code
#18CrossMoCo
93.8
Overall Accuracy
No paperCode
#19OcCo+DGCNNSOTA
90.6
Overall Accuracy· 2020-10-02
Unsupervised Point Cloud Pre-Training via Occlusion Completion Code
#20OcCo+PointNet
89.7
Overall Accuracy· 2020-10-02
Unsupervised Point Cloud Pre-Training via Occlusion Completion Code
#21GPr-Net + Hyp (512)
81.1
Overall Accuracy· 2023-04-12
GPr-Net: Geometric Prototypical Network for Point Cloud Few-Shot Learning Code
#22GPr-Net + Hyp (1024)
80.4
Overall Accuracy· 2023-04-12
GPr-Net: Geometric Prototypical Network for Point Cloud Few-Shot Learning Code
#23GPr-Net + Euc (1024)
74.4
Overall Accuracy· 2023-04-12
GPr-Net: Geometric Prototypical Network for Point Cloud Few-Shot Learning Code
#24GPr-Net + Euc (512)
74
Overall Accuracy· 2023-04-12
GPr-Net: Geometric Prototypical Network for Point Cloud Few-Shot Learning Code
#25PointCNNSOTA
65.41
Overall Accuracy· 2018-01-23
PointCNN: Convolution On $\mathcal{X}$-Transformed Points Code
#26SSFSL+PointNet
63.2
Overall Accuracy· 2020-09-29
Self-Supervised Few-Shot Learning on Point Clouds Code
#27SSFSL+DGCNN
60
Overall Accuracy· 2020-09-29
Self-Supervised Few-Shot Learning on Point Clouds Code
#28PointNetSOTA
51.97
Overall Accuracy· 2016-12-02
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation Code
#29PointNet++
38.53
Overall Accuracy· 2017-06-07
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space Code
#30DGCNN
31.6
Overall Accuracy· 2018-01-24
Dynamic Graph CNN for Learning on Point Clouds Code