Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection

10 Mar 2022  ยท  Eliahu Horwitz, Yedid Hoshen ยท

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.

PDF Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
3D Anomaly Detection and Segmentation MVTEC 3D-AD Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection (FPFH) Segmentation AUPRO 0.924 # 3
Detection AUROC 0.782 # 5
Segmentation AUROC 0.978 # 2
RGB+3D Anomaly Detection and Segmentation MVTEC 3D-AD Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection (BTF) Segmentation AUPRO 0.959 # 4
Detection AUCROC 0.865 # 5
Segmentation AUCROC 0.992 # 3
Depth Anomaly Detection and Segmentation MVTEC 3D-AD Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection (Depth iNet) Segmentation AUPRO 0.755 # 7
Detection AUROC 0.675 # 7
Segmentation AUROC 0.930 # 5
Depth Anomaly Detection and Segmentation MVTEC 3D-AD Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection (NSA) Segmentation AUPRO 0.5572 # 8
Detection AUROC 0.696 # 6
Segmentation AUROC 0.817 # 7
Depth Anomaly Detection and Segmentation MVTEC 3D-AD Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection (RaW) Segmentation AUPRO 0.442 # 9
Detection AUROC 0.573 # 8
Segmentation AUROC 0.771 # 8
Depth Anomaly Detection and Segmentation MVTEC 3D-AD Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection (HoG) Segmentation AUPRO 0.771 # 6
Detection AUROC 0.559 # 9
Segmentation AUROC 0.930 # 5
Depth Anomaly Detection and Segmentation MVTEC 3D-AD Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection (SIFT) Segmentation AUPRO 0.910 # 4
Detection AUROC 0.727 # 5
Segmentation AUROC 0.974 # 3

Methods