Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Network

• Published in: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp. 22207 - 22216
• Main Authors: Li, Wenqiao, Xu, Xiaohao, Gu, Yao, Zheng, Bozhong, Gaol, Shenghua, Wu, Yingna
• Format: Conference Proceeding
• Language: English
• Published: IEEE 16.06.2024
• Subjects: Adaptation models; Anomaly Detection 3D Vision Self-Supervised; Benchmark testing; Location awareness; Point cloud compression; Solid modeling; Three-dimensional displays; Training
• ISSN: 2575-7075
• DOI: 10.1109/CVPR52733.2024.02096

Recently, 3D anomaly detection, a crucial problem in-volving fine-grained geometry discrimination, is getting more attention. However, the lack of abundant real 3D anomaly data limits the scalability of current models. To enable scalable anomaly data collection, we propose a 3D anomaly synthesis pipeline to adapt existing large-scale 3D models for 3D anomaly detection. Specifically, we construct a synthetic dataset, i.e., Anomaly-ShapeNet, based on ShapeNet. Anomaly-ShapeNet consists of 1600 point cloud samples under 40 categories, which provides a rich and varied collection of data, enabling efficient training and enhancing adaptability to industrial scenarios. Meanwhile, to enable scalable representation learning for 3D anomaly localization, we propose a self-supervised method, i.e., It-erative Mask Reconstruction Network (IMRNet). During training, we propose a geometry-aware sample module to preserve potentially anomalous local regions during point cloud down-sampling. Then, we randomly mask out point patches and sent the visible patches to a trans-former for reconstruction-based self-supervision. During testing, the point cloud repeatedly goes through the Mask Reconstruction Network, with each iteration's output be-coming the next input. By merging and contrasting the final reconstructed point cloud with the initial input, our method successfully locates anomalies. Experiments show that IMRNet outperforms previous state-of-the-art methods, achieving 66.1% in I-AUC on our Anomaly-ShapeNet dataset and 72.5% in I-AUC on ReaI3D-AD dataset. Our benchmark will be released at https://github.com/Chopper-233/Anomaly-ShapeNet.