MVTec AD is a dataset for benchmarking anomaly detection methods with a focus on industrial inspection. It contains over 5000 high-resolution images divided into fifteen different object and texture categories. Each category comprises a set of defect-free training images and a test set of images with various kinds of defects as well as images without defects.
Pixel-precise annotations of all anomalies are also provided. More information can be found in our corresponding paper.
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 three folders:
- 'train', which contains the (defect-free) training images
- 'test', which contains the test images
- 'ground_truth', which contains the pixel-precise annotations of anomalous regions
Please note that our dataset is hosted on an FTP server. You need an FTP client software to download them.
Download the whole dataset (4.9 GB)
Download each object category separately:
If you use this dataset in scientific work, please cite our papers:
Paul Bergmann, Kilian Batzner, Michael Fauser, David Sattlegger, Carsten Steger: The MVTec Anomaly Detection Dataset: A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection;
in: International Journal of Computer Vision, January 2021. [pdf]
Paul Bergmann, Michael Fauser, David Sattlegger, Carsten Steger: MVTec AD – A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection;
in: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2019. [pdf]
The data is released under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License (CC BY-NC-SA 4.0). For using the data in a way that falls under the commercial use clause of the license, please contact us via the form below.