For your convenience, we provide a download link for the whole dataset, as well as links for each object category. For each object, the data consist of five folders:
‘train’, which contains the defect-free training images
‘validation’, which contains the defect-free validation images
‘test_public’, which contains test images from every lighting condition together with the corresponding pixel-precise ground truth annotations
‘test_private’, which contains test images captured under the regular lighting condition
‘test_private_mixed’, which contains test images of the same scenes as in ‘test_private’ but captured under varied lighting conditions
MVTec AD is a dataset for benchmarking anomaly detection methods with a focus on industrial inspection. It contains over 5,000 high-resolution images divided into fifteen different object and texture categories.
MVTec 3D-AD is a comprehensive 3D dataset for the task of unsupervised anomaly detection and localization. It contains over 4,000 high-resolution scans acquired by an industrial 3D sensor.
The MVTec logical constraints anomaly detection (MVTec LOCO AD) dataset is intended for the evaluation of unsupervised anomaly localization algorithms. The dataset includes both structural and logical anomalies.
