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/VoteNet (PC-FractalDB)

VoteNet (PC-FractalDB)

Reported on 24 benchmarks across 6 tasks

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

Methodology16 results

  • 3DonSUN-RGBD val
    mAP@0.25· uses extra data
    60.2
    best: 69.7 (Point-GCC+TR3D+FF)
  • 3DonSUN-RGBD val
    mAP@0.5· uses extra data
    35.2
    best: 54 (Point-GCC+TR3D+FF)
  • 3DonScanNetV2
    mAP@0.25· uses extra data
    63.4
    best: 78.8 (DEST (based on V-DETR) (TTA))
  • 3DonScanNetV2
    mAP@0.5· uses extra data
    39.9
    best: 67.9 (DEST (based on V-DETR) (TTA))
  • 2D ClassificationonSUN-RGBD val
    mAP@0.25· uses extra data
    60.2
    best: 69.7 (Point-GCC+TR3D+FF)
  • 2D ClassificationonSUN-RGBD val
    mAP@0.5· uses extra data
    35.2
    best: 54 (Point-GCC+TR3D+FF)
  • 2D ClassificationonScanNetV2
    mAP@0.25· uses extra data
    63.4
    best: 78.8 (DEST (based on V-DETR) (TTA))
  • 2D ClassificationonScanNetV2
    mAP@0.5· uses extra data
    39.9
    best: 67.9 (DEST (based on V-DETR) (TTA))
  • 2D Object DetectiononSUN-RGBD val
    mAP@0.25· uses extra data
    60.2
    best: 69.7 (Point-GCC+TR3D+FF)
  • 2D Object DetectiononSUN-RGBD val
    mAP@0.5· uses extra data
    35.2
    best: 54 (Point-GCC+TR3D+FF)
  • 2D Object DetectiononScanNetV2
    mAP@0.25· uses extra data
    63.4
    best: 78.8 (DEST (based on V-DETR) (TTA))
  • 2D Object DetectiononScanNetV2
    mAP@0.5· uses extra data
    39.9
    best: 67.9 (DEST (based on V-DETR) (TTA))
  • 16konSUN-RGBD val
    mAP@0.25· uses extra data
    60.2
    best: 69.7 (Point-GCC+TR3D+FF)
  • 16konSUN-RGBD val
    mAP@0.5· uses extra data
    35.2
    best: 54 (Point-GCC+TR3D+FF)
  • 16konScanNetV2
    mAP@0.25· uses extra data
    63.4
    best: 78.8 (DEST (based on V-DETR) (TTA))
  • 16konScanNetV2
    mAP@0.5· uses extra data
    39.9
    best: 67.9 (DEST (based on V-DETR) (TTA))

Computer Vision8 results

  • Object DetectiononSUN-RGBD val
    mAP@0.25· uses extra data
    60.2
    best: 69.7 (Point-GCC+TR3D+FF)
  • Object DetectiononSUN-RGBD val
    mAP@0.5· uses extra data
    35.2
    best: 54 (Point-GCC+TR3D+FF)
  • Object DetectiononScanNetV2
    mAP@0.25· uses extra data
    63.4
    best: 78.8 (DEST (based on V-DETR) (TTA))
  • Object DetectiononScanNetV2
    mAP@0.5· uses extra data
    39.9
    best: 67.9 (DEST (based on V-DETR) (TTA))
  • 3D Object DetectiononSUN-RGBD val
    mAP@0.25· uses extra data
    60.2
    best: 69.7 (Point-GCC+TR3D+FF)
  • 3D Object DetectiononSUN-RGBD val
    mAP@0.5· uses extra data
    35.2
    best: 54 (Point-GCC+TR3D+FF)
  • 3D Object DetectiononScanNetV2
    mAP@0.25· uses extra data
    63.4
    best: 78.8 (DEST (based on V-DETR) (TTA))
  • 3D Object DetectiononScanNetV2
    mAP@0.5· uses extra data
    39.9
    best: 67.9 (DEST (based on V-DETR) (TTA))