Pith. sign in

REVIEW 20 cited by

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

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2112.09045 v1 pith:QK73LTEN submitted 2021-12-16 cs.CV

Paul Bergmann , Xin Jin , David Sattlegger , Carsten Steger This is my paper · ORCID
classification cs.CV
keywords anomalydatasetdefectsdetectionobjectanomaly-freecategoriesdata
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original 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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 20 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. MVFM-3DAD: Multi-view Flow Matching for 3D Anomaly Detection via Density Proxy Estimation

    cs.GR 2026-08 conditional novelty 6.0 of 10

    MVFM-3DAD detects and localizes 3D anomalies by learning a flow-matching transport from normal multi-view features to a Gaussian reference and scoring test points by their terminal energy after back-projection.

  2. CL-Anomaly: Layer-Adaptive Mixture-of-Experts with Multimodal Large Language Model for Continual Learning in Anomaly Detection

    cs.CV 2026-07 conditional novelty 6.0 of 10

    A private-plus-shared LoRA MoE with layer-adaptive momentum transfer enables continual anomaly detection on MLLMs and beats prior continual-learning baselines across class, domain, and modality shifts.

  3. Hierarchical Point-Patch Fusion with Adaptive Patch Codebook for 3D Shape Anomaly Detection

    cs.CV 2026-04 conditional novelty 6.0 of 10

    Adaptive multi-scale patch codebooks fused with point features via RoPE cross-attention improve 3D shape anomaly detection, especially for large structural industrial defects.

  4. Multimodal Benchmark for Safety Assessment in Industrial Inspection Scenarios

    cs.RO 2026-01 conditional novelty 6.0 of 10

    A real-world multimodal benchmark with 5,013 annotated inspection instances and a safety-assessment evaluation of 15 vision-language models.

  5. DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup

    cs.CV 2025-08 unverdicted novelty 6.0 of 10

    The submitted text is mismatched: abstract proposes DictAS for anomaly segmentation, while the body is an unrelated statistics paper.

  6. Self-Navigated Residual Mamba for Universal Industrial Anomaly Detection

    cs.CV 2025-08 conditional novelty 6.0 of 10

    SNARM combines memory-bank residuals, self-referential in-image residuals, and residual-guided Mamba scanning to report state-of-the-art anomaly detection scores on three benchmarks.

  7. HyPCV-Former: Hyperbolic Spatio-Temporal Transformer for 3D Point Cloud Video Anomaly Detection

    cs.CV 2025-08 unverdicted novelty 6.0 of 10

    HyPCV-Former embeds point cloud video features in Lorentzian hyperbolic space and uses hyperbolic attention to improve video anomaly detection on two benchmarks.

  8. An aerial color image anomaly dataset for search missions in complex forested terrain

    cs.CV 2025-07 conditional novelty 6.0 of 10

    A new benchmark dataset of 34,424 labels across 10,659 aerial forest images from a real manhunt where standard anomaly detectors perform poorly.

  9. Real-IAD D3: A Real-World 2D/Pseudo-3D/3D Dataset for Industrial Anomaly Detection

    cs.CV 2025-04 conditional novelty 6.0 of 10

    A new 8,450-sample multimodal industrial anomaly detection dataset adds pseudo-3D photometric stereo data to RGB and high-resolution point clouds, with a fusion benchmark that improves average detection accuracy.

  10. Exploring Few-Shot Defect Segmentation in General Industrial Scenarios with Metric Learning and Vision Foundation Models

    cs.CV 2025-02 conditional novelty 6.0 of 10

    A new 12-product industrial benchmark shows foundation models, particularly SAM2 in video track mode, outperform meta-learning for few-shot defect segmentation.

  11. Tuned Reverse Distillation: Enhancing Multimodal Industrial Anomaly Detection with Crossmodal Tuners

    cs.CV 2024-12 conditional novelty 6.0 of 10

    TRD detects and localizes industrial anomalies by distilling each modality through its own branch and using crossmodal filter and amplifier modules to share normal and anomalous cues between modalities.

  12. LIBAD: A Multimodal Anomaly Detection Benchmark for Li-Ion Battery Electrode Manufacturing

    cs.CV 2026-08 conditional novelty 5.0 of 10

    A new multimodal anomaly detection benchmark for battery electrode manufacturing shows that existing methods have high false-positive rates, and a density-aware coreset method modestly improves FPR95.

  13. A Synthetic 3D Gear Dataset for Manufacturing Quality Inspection (MFGNet-Gear)

    cs.CV 2026-07 conditional novelty 5.0 of 10

    A public synthetic 3D gear dataset with 24,000 point-cloud/mesh pairs across 12 designs and 4 quality classes, generated by a reproducible CAD-to-sampling pipeline.

  14. IAENet: An Importance-Aware Ensemble Model for 3D Point Cloud-Based Anomaly Detection

    cs.CV 2025-08 conditional novelty 5.0 of 10

    IAENet fuses 2D and 3D anomaly scores with a learned importance-aware weighting and a margin-based selector loss, achieving state-of-the-art point-level localization on MVTec 3D-AD.

  15. Generative Model-Based Feature Attention Module for Video Action Analysis

    cs.CV 2025-08 conditional novelty 5.0 of 10

    DictAS treats few-shot anomaly segmentation as a sparse dictionary lookup over frozen CLIP features and reports state-of-the-art scores on seven industrial and medical benchmarks.

  16. BridgeNet: A Unified Multimodal Framework for Bridging 2D and 3D Industrial Anomaly Detection

    cs.CV 2025-07 conditional novelty 5.0 of 10

    A shared-parameter RGB-plus-depth network trained with multi-scale Gaussian and texture anomaly generators reaches 99.3% I-AUROC and 97.7% P-AUPRO on MVTec-3D AD, and 95.8% I-AUROC on Eyecandies.

  17. A 3D Multimodal Feature for Infrastructure Anomaly Detection

    cs.CV 2025-02 conditional novelty 5.0 of 10

    Fusing FPFH geometry descriptors with a new 3D intensity histogram improves PatchCore-based crack and water patch detection on 3D point clouds of bridges and tunnels.

  18. GCR: Geometry-Consistent Routing for Task-Agnostic Continual Anomaly Detection

    cs.CV 2026-01 conditional novelty 4.0 of 10

    GCR improves task-agnostic continual anomaly detection by routing in a shared frozen embedding space with geometry-consistent prototype matching, achieving near-zero forgetting on MVTec AD and VisA.

  19. 3DKeyAD: High-Resolution 3D Point Cloud Anomaly Detection via Keypoint-Guided Point Clustering

    cs.CV 2025-07 conditional novelty 4.0 of 10

    Keypoint-guided clustering with multi-prototype registration improves 3D point cloud anomaly detection on Real3D-AD, reaching 0.801 object-level and 0.861 point-level AUROC, though the margin over prior work is small ...

  20. Optimized CNNs for Rapid 3D Point Cloud Object Recognition

    cs.CV 2024-12 reject novelty 2.0 of 10

    A 3D point cloud anomaly detection method combining FPFH, multi-view ResNet18 features, and graph convolution reports slightly higher MVTec 3D-AD scores than prior work, but the claimed sparse-convolution and L1 contr...

Pith tools