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/BFL

BFL

Reported on 18 benchmarks across 8 tasks · 1 paper

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

Computer Vision10 results

  • Instance SegmentationonScanNet(v2)
    mAP· 2025-02-06
    60.6
    best: 62.2 (Relation3D)
    Beyond the Final Layer: Hierarchical Query Fusion Transformer with Agent-Interpolation Initialization for 3D Instance SegmentationarXiv:2502.04139
  • Instance SegmentationonScanNet(v2)
    mAP @ 50· 2025-02-06
    81
    best: 81.6 (Relation3D)
    Beyond the Final Layer: Hierarchical Query Fusion Transformer with Agent-Interpolation Initialization for 3D Instance SegmentationarXiv:2502.04139
  • Instance SegmentationonScanNet(v2)
    mAP@25· 2025-02-06
    88.2
    best: 90.1 (Relation3D)
    Beyond the Final Layer: Hierarchical Query Fusion Transformer with Agent-Interpolation Initialization for 3D Instance SegmentationarXiv:2502.04139
  • 3D Instance SegmentationonScanNet(v2)
    mAP· 2025-02-06
    60.6
    best: 62.2 (Relation3D)
    Beyond the Final Layer: Hierarchical Query Fusion Transformer with Agent-Interpolation Initialization for 3D Instance SegmentationarXiv:2502.04139
  • 3D Instance SegmentationonScanNet(v2)
    mAP @ 50· 2025-02-06
    81
    best: 81.6 (Relation3D)
    Beyond the Final Layer: Hierarchical Query Fusion Transformer with Agent-Interpolation Initialization for 3D Instance SegmentationarXiv:2502.04139
  • 3D Instance SegmentationonScanNet(v2)
    mAP@25· 2025-02-06
    88.2
    best: 90.1 (Relation3D)
    Beyond the Final Layer: Hierarchical Query Fusion Transformer with Agent-Interpolation Initialization for 3D Instance SegmentationarXiv:2502.04139
  • Object DetectiononScanNetV2
    mAP@0.25
    74.6
    best: 78.8 (DEST (based on V-DETR) (TTA))
  • Object DetectiononScanNetV2
    mAP@0.5
    65.3
    best: 67.9 (DEST (based on V-DETR) (TTA))
  • 3D Object DetectiononScanNetV2
    mAP@0.25
    74.6
    best: 78.8 (DEST (based on V-DETR) (TTA))
  • 3D Object DetectiononScanNetV2
    mAP@0.5
    65.3
    best: 67.9 (DEST (based on V-DETR) (TTA))

Methodology8 results

  • 3DonScanNetV2
    mAP@0.25
    74.6
    best: 78.8 (DEST (based on V-DETR) (TTA))
  • 3DonScanNetV2
    mAP@0.5
    65.3
    best: 67.9 (DEST (based on V-DETR) (TTA))
  • 2D ClassificationonScanNetV2
    mAP@0.25
    74.6
    best: 78.8 (DEST (based on V-DETR) (TTA))
  • 2D ClassificationonScanNetV2
    mAP@0.5
    65.3
    best: 67.9 (DEST (based on V-DETR) (TTA))
  • 2D Object DetectiononScanNetV2
    mAP@0.25
    74.6
    best: 78.8 (DEST (based on V-DETR) (TTA))
  • 2D Object DetectiononScanNetV2
    mAP@0.5
    65.3
    best: 67.9 (DEST (based on V-DETR) (TTA))
  • 16konScanNetV2
    mAP@0.25
    74.6
    best: 78.8 (DEST (based on V-DETR) (TTA))
  • 16konScanNetV2
    mAP@0.5
    65.3
    best: 67.9 (DEST (based on V-DETR) (TTA))