Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection
About
Despite significant advances in image anomaly detection and segmentation, few methods use 3D information. We utilize a recently introduced 3D anomaly detection dataset to evaluate whether or not using 3D information is a lost opportunity. First, we present a surprising finding: standard color-only methods outperform all current methods that are explicitly designed to exploit 3D information. This is counter-intuitive as even a simple inspection of the dataset shows that color-only methods are insufficient for images containing geometric anomalies. This motivates the question: how can anomaly detection methods effectively use 3D information? We investigate a range of shape representations including hand-crafted and deep-learning-based; we demonstrate that rotation invariance plays the leading role in the performance. We uncover a simple 3D-only method that beats all recent approaches while not using deep learning, external pre-training datasets, or color information. As the 3D-only method cannot detect color and texture anomalies, we combine it with color-based features, significantly outperforming previous state-of-the-art. Our method, dubbed BTF (Back to the Feature) achieves pixel-wise ROCAUC: 99.3% and PRO: 96.4% on MVTec 3D-AD.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Anomaly Detection | MVTec 3D-AD 1.0 (test) | Mean Score0.924 | 107 | |
| Object-level Anomaly Detection | Anomaly-ShapeNet (test) | ashtray065.1 | 49 | |
| Object-level Anomaly Detection | Real3D-AD 1.0 (test) | Airplane73.8 | 43 | |
| 3D Anomaly Detection | Real3D-AD | Average O-AUROC0.635 | 33 | |
| 3D Anomaly Detection | Anomaly-ShapeNet 1.0 (test) | Avg Rank7 | 31 | |
| Anomaly Segmentation | MVTec 3D-AD | Mean Score99.2 | 30 | |
| 3D Anomaly Detection | Real3D-AD (test) | Airplane73 | 30 | |
| Anomaly Detection | Anomaly-ShapeNet v1 (test) | Cap 0 AUROC0.73 | 26 | |
| Anomaly Localization | MVTec3D | P-AUROC99.2 | 22 | |
| 3D Anomaly Localization | Real3D-AD | Airplane73.8 | 21 |