{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/the-mvtec-3d-ad-dataset-for-unsupervised-3d","title":"The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localization","arxiv_id":"2112.09045","date":"2021-12-16","proceeding":null,"authors":["Paul Bergmann","Xin Jin","David Sattlegger","Carsten Steger"],"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.","url_abs":"https://arxiv.org/abs/2112.09045v1","url_pdf":"https://arxiv.org/pdf/2112.09045v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"the-mvtec-3d-ad-dataset-for-unsupervised-3d","repo_url":"https://github.com/JerryX1110/Awesome-3D-Anomaly-Detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"the-mvtec-3d-ad-dataset-for-unsupervised-3d","repo_url":"https://github.com/openvinotoolkit/anomalib","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"3d-anomaly-detection-and-segmentation","task_name":"3D Anomaly Detection and Segmentation"},{"task_slug":"anomaly-detection","task_name":"Anomaly Detection"},{"task_slug":"depth-anomaly-detection-and-segmentation","task_name":"Depth Anomaly Detection and Segmentation"},{"task_slug":"object","task_name":"Object"},{"task_slug":"rgb-3d-anomaly-detection-and-segmentation","task_name":"RGB+3D Anomaly Detection and Segmentation"},{"task_slug":"rgb-depth-anomaly-detection-and-segmentation","task_name":"RGB+Depth Anomaly Detection and Segmentation"},{"task_slug":"unsupervised-anomaly-detection","task_name":"Unsupervised Anomaly Detection"}],"methods":[],"datasets_introduced":[{"slug":"mvtec-3d-ad","name":"MVTEC 3D-AD","full_name":"THE MVTEC 3D ANOMALY DETECTION DATASET"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-anomaly-detection-and-segmentation-on","task":"3D Anomaly Detection and Segmentation","dataset":"MVTEC 3D-AD","model":"Voxel AE","rank_in_archive_order":8,"of":11,"metrics":{"Detection AUROC":"0.699"},"uses_additional_data":false},{"leaderboard":"/sota/3d-anomaly-detection-and-segmentation-on","task":"3D Anomaly Detection and Segmentation","dataset":"MVTEC 3D-AD","model":"Voxel VM","rank_in_archive_order":9,"of":11,"metrics":{"Detection AUROC":"0.571"},"uses_additional_data":false},{"leaderboard":"/sota/3d-anomaly-detection-and-segmentation-on","task":"3D Anomaly Detection and Segmentation","dataset":"MVTEC 3D-AD","model":"Voxel GAN","rank_in_archive_order":10,"of":11,"metrics":{"Detection AUROC":"0.537"},"uses_additional_data":false},{"leaderboard":"/sota/depth-anomaly-detection-and-segmentation-on","task":"Depth Anomaly Detection and Segmentation","dataset":"MVTEC 3D-AD","model":"Depth VM","rank_in_archive_order":11,"of":13,"metrics":{"Detection AUROC":"0.546","Segmentation AUPRO":"0.374"},"uses_additional_data":false},{"leaderboard":"/sota/depth-anomaly-detection-and-segmentation-on","task":"Depth Anomaly Detection and Segmentation","dataset":"MVTEC 3D-AD","model":"Depth AE","rank_in_archive_order":12,"of":13,"metrics":{"Detection AUROC":"0.546","Segmentation AUPRO":"0.203"},"uses_additional_data":false},{"leaderboard":"/sota/depth-anomaly-detection-and-segmentation-on","task":"Depth Anomaly Detection and Segmentation","dataset":"MVTEC 3D-AD","model":"Depth GAN","rank_in_archive_order":13,"of":13,"metrics":{"Detection AUROC":"0.523","Segmentation AUPRO":"0.143"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-3d-anomaly-detection-and-segmentation-on","task":"RGB+3D Anomaly Detection and Segmentation","dataset":"MVTEC 3D-AD","model":"Voxel VM","rank_in_archive_order":7,"of":9,"metrics":{"Detection AUCROC":"0.609","Segmentation AUPRO":"0.471"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-3d-anomaly-detection-and-segmentation-on","task":"RGB+3D Anomaly Detection and Segmentation","dataset":"MVTEC 3D-AD","model":"Voxel AE","rank_in_archive_order":8,"of":9,"metrics":{"Detection AUCROC":"0.538","Segmentation AUPRO":"0.564"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-3d-anomaly-detection-and-segmentation-on","task":"RGB+3D Anomaly Detection and Segmentation","dataset":"MVTEC 3D-AD","model":"Voxel GAN","rank_in_archive_order":9,"of":9,"metrics":{"Detection AUCROC":"0.517","Segmentation AUPRO":"0.639"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2112.09045","atlas_url":"https://app.syntology.ai/?focus=2112.09045","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}