Examining the Source of Defects from a Mechanical Perspective for 3D Anomaly Detection

Benchmark Model Rank Results
3d-anomaly-detection-and-segmentation-on-mvtecMC4AD#1Detection AUROC: 0.954Segmentation AUROC: 0.946
3d-anomaly-detection-on-anomaly-shapenetMC4AD#1O-AUROC: 0.909P-AUROC: 0.910
3d-anomaly-detection-on-anomaly-shapenet10MC4AD#1O-AUROC: 0.888P-AUROC: 0.937
3d-anomaly-detection-on-real-3d-adMC4AD#1Mean Performance of P. and O.: 0.8115Point AUROC: 0.837