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/ConvPoint

ConvPoint

Reported on 17 benchmarks across 4 tasks · 1 paper · 8 SOTA

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

Medical7 results

  • Semantic SegmentationonS3DIS
    Params (M)· 2019-04-04
    4.1
    best: 41.6 (PointNeXt-XL)
    SOTA
    ConvPoint: Continuous Convolutions for Point Cloud ProcessingarXiv:1904.02375
  • Semantic SegmentationonS3DIS
    oAcc· 2019-04-04
    88.8
    best: 93.3 (Sonata + PTv3)
    SOTA
    ConvPoint: Continuous Convolutions for Point Cloud ProcessingarXiv:1904.02375
  • Semantic SegmentationonDALES
    Overall Accuracy· 2019-04-04
    97.2
    best: 97.8 (KPConv)
    SOTA
    ConvPoint: Continuous Convolutions for Point Cloud ProcessingarXiv:1904.02375
  • Semantic SegmentationonS3DIS
    Mean IoU· 2019-04-04
    68.2
    best: 82.3 (Sonata + PTv3)
    ConvPoint: Continuous Convolutions for Point Cloud ProcessingarXiv:1904.02375
  • Semantic SegmentationonDALES
    mIoU· 2019-04-04
    67.4
    best: 81.1 (KPConv)
    ConvPoint: Continuous Convolutions for Point Cloud ProcessingarXiv:1904.02375
  • Semantic SegmentationonShapeNet-Part
    Class Average IoU· 2019-04-04
    83.4
    best: 87.7 (Feature Geometric Net (FG-Net))
    ConvPoint: Continuous Convolutions for Point Cloud ProcessingarXiv:1904.02375
  • Semantic SegmentationonShapeNet-Part
    Instance Average IoU· 2019-04-04
    85.8
    best: 89.1 (GeomGCNN)
    ConvPoint: Continuous Convolutions for Point Cloud ProcessingarXiv:1904.02375

Audio7 results

  • 10-shot image generationonS3DIS
    Params (M)· 2019-04-04
    4.1
    best: 41.6 (PointNeXt-XL)
    SOTA
    ConvPoint: Continuous Convolutions for Point Cloud ProcessingarXiv:1904.02375
  • 10-shot image generationonS3DIS
    oAcc· 2019-04-04
    88.8
    best: 93.3 (Sonata + PTv3)
    SOTA
    ConvPoint: Continuous Convolutions for Point Cloud ProcessingarXiv:1904.02375
  • 10-shot image generationonDALES
    Overall Accuracy· 2019-04-04
    97.2
    best: 97.8 (KPConv)
    SOTA
    ConvPoint: Continuous Convolutions for Point Cloud ProcessingarXiv:1904.02375
  • 10-shot image generationonS3DIS
    Mean IoU· 2019-04-04
    68.2
    best: 82.3 (Sonata + PTv3)
    ConvPoint: Continuous Convolutions for Point Cloud ProcessingarXiv:1904.02375
  • 10-shot image generationonDALES
    mIoU· 2019-04-04
    67.4
    best: 81.1 (KPConv)
    ConvPoint: Continuous Convolutions for Point Cloud ProcessingarXiv:1904.02375
  • 10-shot image generationonShapeNet-Part
    Class Average IoU· 2019-04-04
    83.4
    best: 87.7 (Feature Geometric Net (FG-Net))
    ConvPoint: Continuous Convolutions for Point Cloud ProcessingarXiv:1904.02375
  • 10-shot image generationonShapeNet-Part
    Instance Average IoU· 2019-04-04
    85.8
    best: 89.1 (GeomGCNN)
    ConvPoint: Continuous Convolutions for Point Cloud ProcessingarXiv:1904.02375

Computer Vision3 results

  • 3D Semantic SegmentationonDALES
    Overall Accuracy· 2019-04-04
    97.2
    best: 97.8 (KPConv)
    SOTA
    ConvPoint: Continuous Convolutions for Point Cloud ProcessingarXiv:1904.02375
  • LIDAR Semantic SegmentationonParis-Lille-3D
    mIOU· 2019-04-04
    0.759
    best: 0.827 (FKAConv)
    SOTA
    ConvPoint: Continuous Convolutions for Point Cloud ProcessingarXiv:1904.02375
  • 3D Semantic SegmentationonDALES
    mIoU· 2019-04-04
    67.4
    best: 81.1 (KPConv)
    ConvPoint: Continuous Convolutions for Point Cloud ProcessingarXiv:1904.02375