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/MC3D-AD

MC3D-AD

Reported on 8 benchmarks across 2 tasks · 1 paper · 4 SOTA

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

Methodology4 results

  • Anomaly DetectiononAnomaly-ShapeNet
    O-AUROC· 2025-05-04
    0.842
    best: 0.909 (MC4AD)
    SOTA
    MC3D-AD: A Unified Geometry-aware Reconstruction Model for Multi-category 3D Anomaly DetectionarXiv:2505.01969
  • Anomaly DetectiononReal 3D-AD
    Object AUROC· 2025-05-04
    0.782
    best: 0.802 (PASDF)
    SOTA
    MC3D-AD: A Unified Geometry-aware Reconstruction Model for Multi-category 3D Anomaly DetectionarXiv:2505.01969
  • Anomaly DetectiononReal 3D-AD
    Mean Performance of P. and O. · 2025-05-04
    0.775
    best: 0.821 (DUS-Net)
    MC3D-AD: A Unified Geometry-aware Reconstruction Model for Multi-category 3D Anomaly DetectionarXiv:2505.01969
  • Anomaly DetectiononReal 3D-AD
    Point AUROC· 2025-05-04
    0.768
    best: 0.898 (GLFM)
    MC3D-AD: A Unified Geometry-aware Reconstruction Model for Multi-category 3D Anomaly DetectionarXiv:2505.01969

Computer Vision4 results

  • 3D Anomaly DetectiononAnomaly-ShapeNet
    O-AUROC· 2025-05-04
    0.842
    best: 0.909 (MC4AD)
    SOTA
    MC3D-AD: A Unified Geometry-aware Reconstruction Model for Multi-category 3D Anomaly DetectionarXiv:2505.01969
  • 3D Anomaly DetectiononReal 3D-AD
    Object AUROC· 2025-05-04
    0.782
    best: 0.802 (PASDF)
    SOTA
    MC3D-AD: A Unified Geometry-aware Reconstruction Model for Multi-category 3D Anomaly DetectionarXiv:2505.01969
  • 3D Anomaly DetectiononReal 3D-AD
    Mean Performance of P. and O. · 2025-05-04
    0.775
    best: 0.821 (DUS-Net)
    MC3D-AD: A Unified Geometry-aware Reconstruction Model for Multi-category 3D Anomaly DetectionarXiv:2505.01969
  • 3D Anomaly DetectiononReal 3D-AD
    Point AUROC· 2025-05-04
    0.768
    best: 0.898 (GLFM)
    MC3D-AD: A Unified Geometry-aware Reconstruction Model for Multi-category 3D Anomaly DetectionarXiv:2505.01969