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/point2vec

point2vec

Reported on 46 benchmarks across 5 tasks · 1 paper · 6 SOTA

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

Computer Vision42 results

Shape Representation Of 3D Point CloudsonModelNet40
Overall Accuracy· uses extra data· 2023-03-29
94.8
best: 95.3 (PointGST)
SOTA
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570
Shape Representation Of 3D Point CloudsonModelNet40 10-way (10-shot)
Overall Accuracy· uses extra data· 2023-03-29
93.9
best: 95 (Point-JEPA)
SOTA
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570
3D Point Cloud ClassificationonModelNet40
Overall Accuracy· uses extra data· 2023-03-29
94.8
best: 95.3 (PointGST)
SOTA
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570
3D Point Cloud ClassificationonModelNet40 10-way (10-shot)
Overall Accuracy· uses extra data· 2023-03-29
93.9
best: 95 (Point-JEPA)
SOTA
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570
3D Point Cloud ReconstructiononModelNet40
Overall Accuracy· uses extra data· 2023-03-29
94.8
best: 95.3 (PointGST)
SOTA
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570
3D Point Cloud ReconstructiononModelNet40 10-way (10-shot)
Overall Accuracy· uses extra data· 2023-03-29
93.9
best: 95 (Point-JEPA)
SOTA
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570
Shape Representation Of 3D Point CloudsonScanObjectNN
Mean Accuracy· uses extra data· 2023-03-29
86
best: 93.8 (GPSFormer)
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570
Shape Representation Of 3D Point CloudsonScanObjectNN
OBJ-BG (OA)· uses extra data· 2023-03-29
91.2
best: 99.48 (PointGST)
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570
Shape Representation Of 3D Point CloudsonScanObjectNN
OBJ-ONLY (OA)· uses extra data· 2023-03-29
90.4
best: 97.76 (PointGST)
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570
Shape Representation Of 3D Point CloudsonScanObjectNN
Overall Accuracy· uses extra data· 2023-03-29
87.5
best: 97.2 (OmniVec2)
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570
Shape Representation Of 3D Point CloudsonModelNet40
Mean Accuracy· uses extra data· 2023-03-29
92
best: 92.4 (ULIP + PointMLP)
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570
Shape Representation Of 3D Point CloudsonModelNet40 10-way (20-shot)
Overall Accuracy· uses extra data· 2023-03-29
95.8
best: 96.5 (ReCon++)
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570
Shape Representation Of 3D Point CloudsonModelNet40 10-way (20-shot)
Standard Deviation· uses extra data· 2023-03-29
3.1
best: 13.5 (PointNet)
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570
Shape Representation Of 3D Point CloudsonModelNet40 5-way (10-shot)
Overall Accuracy· uses extra data· 2023-03-29
97
best: 98 (PointGPT)
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570
Shape Representation Of 3D Point CloudsonModelNet40 5-way (10-shot)
Standard Deviation· uses extra data· 2023-03-29
2.8
best: 16 (PointNet++)
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570
Shape Representation Of 3D Point CloudsonModelNet40 10-way (10-shot)
Standard Deviation· uses extra data· 2023-03-29
4.1
best: 13.5 (PointNet)
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570
Shape Representation Of 3D Point CloudsonModelNet40 5-way (20-shot)
Overall Accuracy· uses extra data· 2023-03-29
98.7
best: 99.5 (ReCon++)
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570
Shape Representation Of 3D Point CloudsonModelNet40 5-way (20-shot)
Standard Deviation· uses extra data· 2023-03-29
1.2
best: 15.5 (PointNet)
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570
3D Point Cloud ClassificationonScanObjectNN
Mean Accuracy· uses extra data· 2023-03-29
86
best: 93.8 (GPSFormer)
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570
3D Point Cloud ClassificationonScanObjectNN
OBJ-BG (OA)· uses extra data· 2023-03-29
91.2
best: 99.48 (PointGST)
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570
3D Point Cloud ClassificationonScanObjectNN
OBJ-ONLY (OA)· uses extra data· 2023-03-29
90.4
best: 97.76 (PointGST)
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570
3D Point Cloud ClassificationonScanObjectNN
Overall Accuracy· uses extra data· 2023-03-29
87.5
best: 97.2 (OmniVec2)
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570
3D Point Cloud ClassificationonModelNet40
Mean Accuracy· uses extra data· 2023-03-29
92
best: 92.4 (ULIP + PointMLP)
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570
3D Point Cloud ClassificationonModelNet40 10-way (20-shot)
Overall Accuracy· uses extra data· 2023-03-29
95.8
best: 96.5 (ReCon++)
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570
3D Point Cloud ClassificationonModelNet40 10-way (20-shot)
Standard Deviation· uses extra data· 2023-03-29
3.1
best: 13.5 (PointNet)
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570
3D Point Cloud ClassificationonModelNet40 5-way (10-shot)
Overall Accuracy· uses extra data· 2023-03-29
97
best: 98 (PointGPT)
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570
3D Point Cloud ClassificationonModelNet40 5-way (10-shot)
Standard Deviation· uses extra data· 2023-03-29
2.8
best: 16 (PointNet++)
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570
3D Point Cloud ClassificationonModelNet40 10-way (10-shot)
Standard Deviation· uses extra data· 2023-03-29
4.1
best: 13.5 (PointNet)
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570
3D Point Cloud ClassificationonModelNet40 5-way (20-shot)
Overall Accuracy· uses extra data· 2023-03-29
98.7
best: 99.5 (ReCon++)
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570
3D Point Cloud ClassificationonModelNet40 5-way (20-shot)
Standard Deviation· uses extra data· 2023-03-29
1.2
best: 15.5 (PointNet)
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570
3D Point Cloud ReconstructiononScanObjectNN
Mean Accuracy· uses extra data· 2023-03-29
86
best: 93.8 (GPSFormer)
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570
3D Point Cloud ReconstructiononScanObjectNN
OBJ-BG (OA)· uses extra data· 2023-03-29
91.2
best: 99.48 (PointGST)
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570
3D Point Cloud ReconstructiononScanObjectNN
OBJ-ONLY (OA)· uses extra data· 2023-03-29
90.4
best: 97.76 (PointGST)
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570
3D Point Cloud ReconstructiononScanObjectNN
Overall Accuracy· uses extra data· 2023-03-29
87.5
best: 97.2 (OmniVec2)
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570
3D Point Cloud ReconstructiononModelNet40
Mean Accuracy· uses extra data· 2023-03-29
92
best: 92.4 (ULIP + PointMLP)
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570
3D Point Cloud ReconstructiononModelNet40 10-way (20-shot)
Overall Accuracy· uses extra data· 2023-03-29
95.8
best: 96.5 (ReCon++)
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570
3D Point Cloud ReconstructiononModelNet40 10-way (20-shot)
Standard Deviation· uses extra data· 2023-03-29
3.1
best: 13.5 (PointNet)
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570
3D Point Cloud ReconstructiononModelNet40 5-way (10-shot)
Overall Accuracy· uses extra data· 2023-03-29
97
best: 98 (PointGPT)
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570
3D Point Cloud ReconstructiononModelNet40 5-way (10-shot)
Standard Deviation· uses extra data· 2023-03-29
2.8
best: 16 (PointNet++)
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570
3D Point Cloud ReconstructiononModelNet40 10-way (10-shot)
Standard Deviation· uses extra data· 2023-03-29
4.1
best: 13.5 (PointNet)
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570
3D Point Cloud ReconstructiononModelNet40 5-way (20-shot)
Overall Accuracy· uses extra data· 2023-03-29
98.7
best: 99.5 (ReCon++)
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570
3D Point Cloud ReconstructiononModelNet40 5-way (20-shot)
Standard Deviation· uses extra data· 2023-03-29
1.2
best: 15.5 (PointNet)
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570

Medical2 results

Semantic SegmentationonShapeNet-Part
Class Average IoU· uses extra data· 2023-03-29
84.6
best: 87.7 (Feature Geometric Net (FG-Net))
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570
Semantic SegmentationonShapeNet-Part
Instance Average IoU· uses extra data· 2023-03-29
86.3
best: 89.1 (GeomGCNN)
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570

Audio2 results

10-shot image generationonShapeNet-Part
Class Average IoU· uses extra data· 2023-03-29
84.6
best: 87.7 (Feature Geometric Net (FG-Net))
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570
10-shot image generationonShapeNet-Part
Instance Average IoU· uses extra data· 2023-03-29
86.3
best: 89.1 (GeomGCNN)
Point2Vec for Self-Supervised Representation Learning on Point Clouds arXiv:2303.16570