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/Point-TnT

Point-TnT

Reported on 9 benchmarks across 3 tasks · 1 paper

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

Computer Vision9 results

  • Shape Representation Of 3D Point CloudsonScanObjectNN
    Mean Accuracy· 2022-04-08
    81
    best: 93.8 (GPSFormer)
    Points to Patches: Enabling the Use of Self-Attention for 3D Shape RecognitionarXiv:2204.03957
  • Shape Representation Of 3D Point CloudsonScanObjectNN
    Overall Accuracy· 2022-04-08
    83.5
    best: 97.2 (OmniVec2)
    Points to Patches: Enabling the Use of Self-Attention for 3D Shape RecognitionarXiv:2204.03957
  • Shape Representation Of 3D Point CloudsonModelNet40
    Overall Accuracy· 2022-04-08
    92.6
    best: 95.3 (PointGST)
    Points to Patches: Enabling the Use of Self-Attention for 3D Shape RecognitionarXiv:2204.03957
  • 3D Point Cloud ClassificationonScanObjectNN
    Mean Accuracy· 2022-04-08
    81
    best: 93.8 (GPSFormer)
    Points to Patches: Enabling the Use of Self-Attention for 3D Shape RecognitionarXiv:2204.03957
  • 3D Point Cloud ClassificationonScanObjectNN
    Overall Accuracy· 2022-04-08
    83.5
    best: 97.2 (OmniVec2)
    Points to Patches: Enabling the Use of Self-Attention for 3D Shape RecognitionarXiv:2204.03957
  • 3D Point Cloud ClassificationonModelNet40
    Overall Accuracy· 2022-04-08
    92.6
    best: 95.3 (PointGST)
    Points to Patches: Enabling the Use of Self-Attention for 3D Shape RecognitionarXiv:2204.03957
  • 3D Point Cloud ReconstructiononScanObjectNN
    Mean Accuracy· 2022-04-08
    81
    best: 93.8 (GPSFormer)
    Points to Patches: Enabling the Use of Self-Attention for 3D Shape RecognitionarXiv:2204.03957
  • 3D Point Cloud ReconstructiononScanObjectNN
    Overall Accuracy· 2022-04-08
    83.5
    best: 97.2 (OmniVec2)
    Points to Patches: Enabling the Use of Self-Attention for 3D Shape RecognitionarXiv:2204.03957
  • 3D Point Cloud ReconstructiononModelNet40
    Overall Accuracy· 2022-04-08
    92.6
    best: 95.3 (PointGST)
    Points to Patches: Enabling the Use of Self-Attention for 3D Shape RecognitionarXiv:2204.03957