TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

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

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

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

Models/OTMae3D

OTMae3D

Reported on 43 benchmarks across 5 tasks

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

Computer Vision39 results

  • Shape Representation Of 3D Point CloudsonScanObjectNN
    FLOPs· uses extra data
    6.29
  • Shape Representation Of 3D Point CloudsonScanObjectNN
    OBJ-BG (OA)· uses extra data
    92.9
    best: 99.48 (PointGST)
  • Shape Representation Of 3D Point CloudsonScanObjectNN
    OBJ-ONLY (OA)· uses extra data
    92.3
    best: 97.76 (PointGST)
  • Shape Representation Of 3D Point CloudsonScanObjectNN
    Overall Accuracy· uses extra data
    89
    best: 97.2 (OmniVec2)
  • Shape Representation Of 3D Point CloudsonModelNet40
    Overall Accuracy· uses extra data
    94.5
    best: 95.3 (PointGST)
  • Shape Representation Of 3D Point CloudsonModelNet40 10-way (20-shot)
    Overall Accuracy· uses extra data
    95.6
    best: 96.5 (ReCon++)
  • Shape Representation Of 3D Point CloudsonModelNet40 10-way (20-shot)
    Standard Deviation· uses extra data
    2.6
    best: 13.5 (PointNet)
  • Shape Representation Of 3D Point CloudsonModelNet40 5-way (10-shot)
    Overall Accuracy· uses extra data
    97.2
    best: 98 (PointGPT)
  • Shape Representation Of 3D Point CloudsonModelNet40 5-way (10-shot)
    Standard Deviation· uses extra data
    2.3
    best: 16 (PointNet++)
  • Shape Representation Of 3D Point CloudsonModelNet40 10-way (10-shot)
    Overall Accuracy· uses extra data
    93.2
    best: 95 (Point-JEPA)
  • Shape Representation Of 3D Point CloudsonModelNet40 10-way (10-shot)
    Standard Deviation· uses extra data
    3.4
    best: 13.5 (PointNet)
  • Shape Representation Of 3D Point CloudsonModelNet40 5-way (20-shot)
    Overall Accuracy· uses extra data
    98.7
    best: 99.5 (ReCon++)
  • Shape Representation Of 3D Point CloudsonModelNet40 5-way (20-shot)
    Standard Deviation· uses extra data
    1.2
    best: 15.5 (PointNet)
  • 3D Point Cloud ClassificationonScanObjectNN
    FLOPs· uses extra data
    6.29
  • 3D Point Cloud ClassificationonScanObjectNN
    OBJ-BG (OA)· uses extra data
    92.9
    best: 99.48 (PointGST)
  • 3D Point Cloud ClassificationonScanObjectNN
    OBJ-ONLY (OA)· uses extra data
    92.3
    best: 97.76 (PointGST)
  • 3D Point Cloud ClassificationonScanObjectNN
    Overall Accuracy· uses extra data
    89
    best: 97.2 (OmniVec2)
  • 3D Point Cloud ClassificationonModelNet40
    Overall Accuracy· uses extra data
    94.5
    best: 95.3 (PointGST)
  • 3D Point Cloud ClassificationonModelNet40 10-way (20-shot)
    Overall Accuracy· uses extra data
    95.6
    best: 96.5 (ReCon++)
  • 3D Point Cloud ClassificationonModelNet40 10-way (20-shot)
    Standard Deviation· uses extra data
    2.6
    best: 13.5 (PointNet)
  • 3D Point Cloud ClassificationonModelNet40 5-way (10-shot)
    Overall Accuracy· uses extra data
    97.2
    best: 98 (PointGPT)
  • 3D Point Cloud ClassificationonModelNet40 5-way (10-shot)
    Standard Deviation· uses extra data
    2.3
    best: 16 (PointNet++)
  • 3D Point Cloud ClassificationonModelNet40 10-way (10-shot)
    Overall Accuracy· uses extra data
    93.2
    best: 95 (Point-JEPA)
  • 3D Point Cloud ClassificationonModelNet40 10-way (10-shot)
    Standard Deviation· uses extra data
    3.4
    best: 13.5 (PointNet)
  • 3D Point Cloud ClassificationonModelNet40 5-way (20-shot)
    Overall Accuracy· uses extra data
    98.7
    best: 99.5 (ReCon++)
  • 3D Point Cloud ClassificationonModelNet40 5-way (20-shot)
    Standard Deviation· uses extra data
    1.2
    best: 15.5 (PointNet)
  • 3D Point Cloud ReconstructiononScanObjectNN
    FLOPs· uses extra data
    6.29
  • 3D Point Cloud ReconstructiononScanObjectNN
    OBJ-BG (OA)· uses extra data
    92.9
    best: 99.48 (PointGST)
  • 3D Point Cloud ReconstructiononScanObjectNN
    OBJ-ONLY (OA)· uses extra data
    92.3
    best: 97.76 (PointGST)
  • 3D Point Cloud ReconstructiononScanObjectNN
    Overall Accuracy· uses extra data
    89
    best: 97.2 (OmniVec2)
  • 3D Point Cloud ReconstructiononModelNet40
    Overall Accuracy· uses extra data
    94.5
    best: 95.3 (PointGST)
  • 3D Point Cloud ReconstructiononModelNet40 10-way (20-shot)
    Overall Accuracy· uses extra data
    95.6
    best: 96.5 (ReCon++)
  • 3D Point Cloud ReconstructiononModelNet40 10-way (20-shot)
    Standard Deviation· uses extra data
    2.6
    best: 13.5 (PointNet)
  • 3D Point Cloud ReconstructiononModelNet40 5-way (10-shot)
    Overall Accuracy· uses extra data
    97.2
    best: 98 (PointGPT)
  • 3D Point Cloud ReconstructiononModelNet40 5-way (10-shot)
    Standard Deviation· uses extra data
    2.3
    best: 16 (PointNet++)
  • 3D Point Cloud ReconstructiononModelNet40 10-way (10-shot)
    Overall Accuracy· uses extra data
    93.2
    best: 95 (Point-JEPA)
  • 3D Point Cloud ReconstructiononModelNet40 10-way (10-shot)
    Standard Deviation· uses extra data
    3.4
    best: 13.5 (PointNet)
  • 3D Point Cloud ReconstructiononModelNet40 5-way (20-shot)
    Overall Accuracy· uses extra data
    98.7
    best: 99.5 (ReCon++)
  • 3D Point Cloud ReconstructiononModelNet40 5-way (20-shot)
    Standard Deviation· uses extra data
    1.2
    best: 15.5 (PointNet)

Medical2 results

  • Semantic SegmentationonShapeNet-Part
    Class Average IoU· uses extra data
    85.1
    best: 87.7 (Feature Geometric Net (FG-Net))
  • Semantic SegmentationonShapeNet-Part
    Instance Average IoU· uses extra data
    86.8
    best: 89.1 (GeomGCNN)

Audio2 results

  • 10-shot image generationonShapeNet-Part
    Class Average IoU· uses extra data
    85.1
    best: 87.7 (Feature Geometric Net (FG-Net))
  • 10-shot image generationonShapeNet-Part
    Instance Average IoU· uses extra data
    86.8
    best: 89.1 (GeomGCNN)