Complementary Pseudo Multimodal Feature for Point Cloud Anomaly Detection

Benchmark Model Rank Results
3d-anomaly-detection-and-segmentation-on-mvtecCPMF (2D+3D)#2Detection AUROC: 0.9515Segmentation AUROC: 0.9781
3d-anomaly-detection-and-segmentation-on-mvtecCPMF (2D)#5Detection AUROC: 0.8918Segmentation AUROC: 0.9730
3d-anomaly-detection-and-segmentation-on-mvtecCPMF (3D)#6Detection AUROC: 0.8304Segmentation AUROC: 0.9780
depth-anomaly-detection-and-segmentation-onCPMF (2D+3D)#2Segmentation AUPRO: 0.9293Detection AUROC: 0.9515
depth-anomaly-detection-and-segmentation-onCPMF (3D)#3Segmentation AUPRO: 0.9230Detection AUROC: 0.8304
depth-anomaly-detection-and-segmentation-onCPMF (2D)#4Segmentation AUPRO: 0.9145Detection AUROC: 0.8918