Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/Point-BERT

Point-BERT

Reported on 36 benchmarks across 3 tasks · 1 paper · 12 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision36 results

Shape Representation Of 3D Point CloudsonModelNet40 10-way (20-shot)
Overall Accuracy· uses extra data· 2021-11-29
92.7
best: 96.5 (ReCon++)
SOTA
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling arXiv:2111.14819
Shape Representation Of 3D Point CloudsonModelNet40 5-way (10-shot)
Overall Accuracy· uses extra data· 2021-11-29
94.6
best: 98 (PointGPT)
SOTA
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling arXiv:2111.14819
Shape Representation Of 3D Point CloudsonModelNet40 10-way (10-shot)
Overall Accuracy· uses extra data· 2021-11-29
91
best: 95 (Point-JEPA)
SOTA
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling arXiv:2111.14819
Shape Representation Of 3D Point CloudsonModelNet40 5-way (20-shot)
Overall Accuracy· uses extra data· 2021-11-29
96.3
best: 99.5 (ReCon++)
SOTA
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling arXiv:2111.14819
3D Point Cloud ClassificationonModelNet40 10-way (20-shot)
Overall Accuracy· uses extra data· 2021-11-29
92.7
best: 96.5 (ReCon++)
SOTA
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling arXiv:2111.14819
3D Point Cloud ClassificationonModelNet40 5-way (10-shot)
Overall Accuracy· uses extra data· 2021-11-29
94.6
best: 98 (PointGPT)
SOTA
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling arXiv:2111.14819
3D Point Cloud ClassificationonModelNet40 10-way (10-shot)
Overall Accuracy· uses extra data· 2021-11-29
91
best: 95 (Point-JEPA)
SOTA
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling arXiv:2111.14819
3D Point Cloud ClassificationonModelNet40 5-way (20-shot)
Overall Accuracy· uses extra data· 2021-11-29
96.3
best: 99.5 (ReCon++)
SOTA
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling arXiv:2111.14819
3D Point Cloud ReconstructiononModelNet40 10-way (20-shot)
Overall Accuracy· uses extra data· 2021-11-29
92.7
best: 96.5 (ReCon++)
SOTA
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling arXiv:2111.14819
3D Point Cloud ReconstructiononModelNet40 5-way (10-shot)
Overall Accuracy· uses extra data· 2021-11-29
94.6
best: 98 (PointGPT)
SOTA
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling arXiv:2111.14819
3D Point Cloud ReconstructiononModelNet40 10-way (10-shot)
Overall Accuracy· uses extra data· 2021-11-29
91
best: 95 (Point-JEPA)
SOTA
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling arXiv:2111.14819
3D Point Cloud ReconstructiononModelNet40 5-way (20-shot)
Overall Accuracy· uses extra data· 2021-11-29
96.3
best: 99.5 (ReCon++)
SOTA
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling arXiv:2111.14819
Shape Representation Of 3D Point CloudsonScanObjectNN
OBJ-BG (OA)· uses extra data· 2021-11-29
87.43
best: 99.48 (PointGST)
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling arXiv:2111.14819
Shape Representation Of 3D Point CloudsonScanObjectNN
OBJ-ONLY (OA)· uses extra data· 2021-11-29
88.12
best: 97.76 (PointGST)
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling arXiv:2111.14819
Shape Representation Of 3D Point CloudsonScanObjectNN
Overall Accuracy· uses extra data· 2021-11-29
83.1
best: 97.2 (OmniVec2)
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling arXiv:2111.14819
Shape Representation Of 3D Point CloudsonModelNet40
Overall Accuracy· uses extra data· 2021-11-29
93.8
best: 95.3 (PointGST)
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling arXiv:2111.14819
Shape Representation Of 3D Point CloudsonModelNet40 10-way (20-shot)
Standard Deviation· uses extra data· 2021-11-29
5.1
best: 13.5 (PointNet)
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling arXiv:2111.14819
Shape Representation Of 3D Point CloudsonModelNet40 5-way (10-shot)
Standard Deviation· uses extra data· 2021-11-29
3.1
best: 16 (PointNet++)
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling arXiv:2111.14819
Shape Representation Of 3D Point CloudsonModelNet40 10-way (10-shot)
Standard Deviation· uses extra data· 2021-11-29
5.4
best: 13.5 (PointNet)
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling arXiv:2111.14819
Shape Representation Of 3D Point CloudsonModelNet40 5-way (20-shot)
Standard Deviation· uses extra data· 2021-11-29
2.7
best: 15.5 (PointNet)
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling arXiv:2111.14819
3D Point Cloud ClassificationonScanObjectNN
OBJ-BG (OA)· uses extra data· 2021-11-29
87.43
best: 99.48 (PointGST)
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling arXiv:2111.14819
3D Point Cloud ClassificationonScanObjectNN
OBJ-ONLY (OA)· uses extra data· 2021-11-29
88.12
best: 97.76 (PointGST)
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling arXiv:2111.14819
3D Point Cloud ClassificationonScanObjectNN
Overall Accuracy· uses extra data· 2021-11-29
83.1
best: 97.2 (OmniVec2)
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling arXiv:2111.14819
3D Point Cloud ClassificationonModelNet40
Overall Accuracy· uses extra data· 2021-11-29
93.8
best: 95.3 (PointGST)
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling arXiv:2111.14819
3D Point Cloud ClassificationonModelNet40 10-way (20-shot)
Standard Deviation· uses extra data· 2021-11-29
5.1
best: 13.5 (PointNet)
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling arXiv:2111.14819
3D Point Cloud ClassificationonModelNet40 5-way (10-shot)
Standard Deviation· uses extra data· 2021-11-29
3.1
best: 16 (PointNet++)
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling arXiv:2111.14819
3D Point Cloud ClassificationonModelNet40 10-way (10-shot)
Standard Deviation· uses extra data· 2021-11-29
5.4
best: 13.5 (PointNet)
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling arXiv:2111.14819
3D Point Cloud ClassificationonModelNet40 5-way (20-shot)
Standard Deviation· uses extra data· 2021-11-29
2.7
best: 15.5 (PointNet)
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling arXiv:2111.14819
3D Point Cloud ReconstructiononScanObjectNN
OBJ-BG (OA)· uses extra data· 2021-11-29
87.43
best: 99.48 (PointGST)
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling arXiv:2111.14819
3D Point Cloud ReconstructiononScanObjectNN
OBJ-ONLY (OA)· uses extra data· 2021-11-29
88.12
best: 97.76 (PointGST)
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling arXiv:2111.14819
3D Point Cloud ReconstructiononScanObjectNN
Overall Accuracy· uses extra data· 2021-11-29
83.1
best: 97.2 (OmniVec2)
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling arXiv:2111.14819
3D Point Cloud ReconstructiononModelNet40
Overall Accuracy· uses extra data· 2021-11-29
93.8
best: 95.3 (PointGST)
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling arXiv:2111.14819
3D Point Cloud ReconstructiononModelNet40 10-way (20-shot)
Standard Deviation· uses extra data· 2021-11-29
5.1
best: 13.5 (PointNet)
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling arXiv:2111.14819
3D Point Cloud ReconstructiononModelNet40 5-way (10-shot)
Standard Deviation· uses extra data· 2021-11-29
3.1
best: 16 (PointNet++)
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling arXiv:2111.14819
3D Point Cloud ReconstructiononModelNet40 10-way (10-shot)
Standard Deviation· uses extra data· 2021-11-29
5.4
best: 13.5 (PointNet)
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling arXiv:2111.14819
3D Point Cloud ReconstructiononModelNet40 5-way (20-shot)
Standard Deviation· uses extra data· 2021-11-29
2.7
best: 15.5 (PointNet)
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling arXiv:2111.14819