</> Code with Papers by Syntology

Datasets › MVTEC 3D-AD

MVTEC 3D-AD (THE MVTEC 3D ANOMALY DETECTION DATASET)

Introduced by Paul Bergmann et al. in The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localization16 Dec 2021 archive 2025-07-28

MVTec 3D Anomaly Detection Dataset (MVTec 3D-AD) is a comprehensive 3D dataset for the task of unsupervised anomaly detection and localization. It contains over 4000 high-resolution scans acquired by an industrial 3D sensor. Each of the 10 different object categories comprises a set of defect-free training and validation samples and a test set of samples with various kinds of defects. Precise ground-truth annotations are provided for each anomalous test sample.

HomepageBenchmarksPapers JSON

Benchmarks archive 2025-07-28

All 4 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Depth Anomaly Detection and Segmentation MVTEC 3D-AD TransFusion Segmentation AUPRO 0.947 TransFusion -- A Transparency-Based Diffusion Model for... maticfuc/eccv_transfusion 13 Compare
3D Anomaly Detection and Segmentation MVTEC 3D-AD MC4AD Detection AUROC 0.954 Examining the Source of Defects from a Mechanical... hzzzzzhappy/mc4ad 11 Compare
RGB+3D Anomaly Detection and Segmentation MVTEC 3D-AD TransFusion Detection AUCROC 0.982 TransFusion -- A Transparency-Based Diffusion Model for... maticfuc/eccv_transfusion 9 Compare
Anomaly Detection MVTEC 3D-AD CDO Segmentation AUPRO 93.75 Collaborative Discrepancy Optimization for Reliable... caoyunkang/CDO 2 Compare

Papers archive 2025-07-28

12 shown of 12 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 45. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
Examining the Source of Defects from a Mechanical Perspective for 3D Anomaly Detection 1 1 9 May 2025 not harvested
Boosting Global-Local Feature Matching via Anomaly Synthesis for Multi-Class Point Cloud Anomaly Detection 1 1 21 Feb 2025 not harvested
TransFusion -- A Transparency-Based Diffusion Model for Anomaly Detection 1 2 16 Nov 2023 ran 1 of 1 samples (0 unverified)
Cheating Depth: Enhancing 3D Surface Anomaly Detection via Depth Simulation 1 2 2 Nov 2023 ran 1 of 2 samples (1 unverified)
Complementary Pseudo Multimodal Feature for Point Cloud Anomaly Detection 2 6 23 Mar 2023 ran 1 of 1 samples (0 unverified)
Multimodal Industrial Anomaly Detection via Hybrid Fusion 1 1 1 Mar 2023 ran 3 of 9 samples (6 unverified)
Collaborative Discrepancy Optimization for Reliable Image Anomaly Localization 1 1 17 Feb 2023 ran 3 of 6 samples (3 unverified)
Shape-Guided: Shape-Guided Dual-Memory Learning for 3D Anomaly Detection 1 2 27 Jan 2023 not harvested
Asymmetric Student-Teacher Networks for Industrial Anomaly Detection 1 2 14 Oct 2022 not harvested
Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection 1 7 10 Mar 2022 ran 1 of 9 samples (8 unverified; 1 pointer-only for licence)
Anomaly Detection in 3D Point Clouds using Deep Geometric Descriptors 0 1 23 Feb 2022 not harvested
The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localization 2 9 16 Dec 2021 not harvested

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

Anomaly Detection3D Anomaly Detection and SegmentationDepth Anomaly Detection and SegmentationRGB+3D Anomaly Detection and Segmentation

License archive 2025-07-28

CC BY-NC-SA 4.0

Modalities archive 2025-07-28

ImagesPoint cloud

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • MVTEC 3D-AD

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections