TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detect...

The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localization

Paul Bergmann, Xin Jin, David Sattlegger, Carsten Steger

2021-12-163D Anomaly Detection and SegmentationUnsupervised Anomaly DetectionAnomaly DetectionDepth Anomaly Detection and SegmentationRGB+3D Anomaly Detection and Segmentation
PaperPDFCodeCode

Abstract

We introduce the first comprehensive 3D dataset for the task of unsupervised anomaly detection and localization. It is inspired by real-world visual inspection scenarios in which a model has to detect various types of defects on manufactured products, even if it is trained only on anomaly-free data. There are defects that manifest themselves as anomalies in the geometric structure of an object. These cause significant deviations in a 3D representation of the data. We employed a high-resolution industrial 3D sensor to acquire depth scans of 10 different object categories. For all object categories, we present a training and validation set, each of which solely consists of scans of anomaly-free samples. The corresponding test sets contain samples showing various defects such as scratches, dents, holes, contaminations, or deformations. Precise ground-truth annotations are provided for every anomalous test sample. An initial benchmark of 3D anomaly detection methods on our dataset indicates a considerable room for improvement.

Results

TaskDatasetMetricValueModel
Anomaly DetectionMVTEC 3D-ADDetection AUROC0.699Voxel AE
Anomaly DetectionMVTEC 3D-ADDetection AUROC0.571Voxel VM
Anomaly DetectionMVTEC 3D-ADDetection AUROC0.537Voxel GAN
Anomaly DetectionMVTEC 3D-ADDetection AUCROC0.609Voxel VM
Anomaly DetectionMVTEC 3D-ADSegmentation AUPRO0.471Voxel VM
Anomaly DetectionMVTEC 3D-ADDetection AUCROC0.538Voxel AE
Anomaly DetectionMVTEC 3D-ADSegmentation AUPRO0.564Voxel AE
Anomaly DetectionMVTEC 3D-ADDetection AUCROC0.517Voxel GAN
Anomaly DetectionMVTEC 3D-ADSegmentation AUPRO0.639Voxel GAN
Anomaly DetectionMVTEC 3D-ADDetection AUROC0.546Depth VM
Anomaly DetectionMVTEC 3D-ADSegmentation AUPRO0.374Depth VM
Anomaly DetectionMVTEC 3D-ADDetection AUROC0.546Depth AE
Anomaly DetectionMVTEC 3D-ADSegmentation AUPRO0.203Depth AE
Anomaly DetectionMVTEC 3D-ADDetection AUROC0.523Depth GAN
Anomaly DetectionMVTEC 3D-ADSegmentation AUPRO0.143Depth GAN

Related Papers

Multi-Stage Prompt Inference Attacks on Enterprise LLM Systems2025-07-213DKeyAD: High-Resolution 3D Point Cloud Anomaly Detection via Keypoint-Guided Point Clustering2025-07-17A Semi-Supervised Learning Method for the Identification of Bad Exposures in Large Imaging Surveys2025-07-17A Privacy-Preserving Framework for Advertising Personalization Incorporating Federated Learning and Differential Privacy2025-07-16Bridge Feature Matching and Cross-Modal Alignment with Mutual-filtering for Zero-shot Anomaly Detection2025-07-15Adversarial Activation Patching: A Framework for Detecting and Mitigating Emergent Deception in Safety-Aligned Transformers2025-07-12Towards High-Resolution 3D Anomaly Detection: A Scalable Dataset and Real-Time Framework for Subtle Industrial Defects2025-07-10seMCD: Sequentially implemented Monte Carlo depth computation with statistical guarantees2025-07-08