Shape-Guided: Shape-Guided Dual-Memory Learning for 3D Anomaly Detection
We present a shape-guided expert-learning framework to tackle the problem of unsupervised 3D anomaly detection. Our method is established on the effectiveness of two specialized expert models and their synergy to localize anomalous regions from color and shape modalities. The first expert utilizes geometric information to probe 3D structural anomalies by modeling the implicit distance fields around local shapes. The second expert considers the 2D RGB features associated with the first expert to identify color appearance irregularities on the local shapes. We use the two experts to build the dual memory banks from the anomaly-free training samples and perform shape-guided inference to pinpoint the defects in the testing samples. Owing to the per-point 3D representation and the effective fusion scheme of complementary modalities, our method efficiently achieves state-of-the-art performance on the MVTec 3D-AD dataset with better recall and lower false positive rates, as preferred in real applications.
PDF AbstractCode
Datasets
MVTEC 3D-AD
Results from the Paper
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Uses Extra Training Data |
Benchmark |
|---|---|---|---|---|---|---|---|
| 3D Anomaly Detection and Segmentation | MVTEC 3D-AD | Shape-Guided (only SDF) | Segmentation AUPRO | 0.931 | # 1 | ||
| Detection AUROC | 0.916 | # 2 | |||||
| Segmentation AUROC | 0.978 | # 2 | |||||
| RGB+3D Anomaly Detection and Segmentation | MVTEC 3D-AD | Shape-Guided | Segmentation AUPRO | 0.976 | # 1 | ||
| Detection AUCROC | 0.947 | # 2 | |||||
| Segmentation AUCROC | 0.996 | # 1 |
