Shape-Guided

Reported on 3 benchmarks across 1 task

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

Methodology3 results

Anomaly DetectiononMVTEC 3D-AD
Detection AUCROC· uses extra data
0.947
best: 0.982 (TransFusion)
Anomaly DetectiononMVTEC 3D-AD
Segmentation AUCROC· uses extra data
0.996
Anomaly DetectiononMVTEC 3D-AD
Segmentation AUPRO· uses extra data
0.976
best: 93.75 (CDO)