Saved in:
Bibliographic Details
Main Authors: Liang, Hanzhe, Zhang, Luocheng, Xia, Junyang, Zhou, HanLiang, Guo, Bingyang, Xie, Yingxi, Gao, Can, Yu, Ruiyun, Wang, Jinbao, Li, Pan
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.01171
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917378116288512
author Liang, Hanzhe
Zhang, Luocheng
Xia, Junyang
Zhou, HanLiang
Guo, Bingyang
Xie, Yingxi
Gao, Can
Yu, Ruiyun
Wang, Jinbao
Li, Pan
author_facet Liang, Hanzhe
Zhang, Luocheng
Xia, Junyang
Zhou, HanLiang
Guo, Bingyang
Xie, Yingxi
Gao, Can
Yu, Ruiyun
Wang, Jinbao
Li, Pan
contents Although self-supervised 3D anomaly detection assumes that acquiring high-precision point clouds is computationally expensive, in real manufacturing scenarios it is often feasible to collect a limited number of anomalous samples. Therefore, we study open-set supervised 3D anomaly detection, where the model is trained with only normal samples and a small number of known anomalous samples, aiming to identify unknown anomalies at test time. We present Open-Industry, a high-quality industrial dataset containing 15 categories, each with five real anomaly types collected from production lines. We first adapt general open-set anomaly detection methods to accommodate 3D point cloud inputs better. Building upon this, we propose Open3D-AD, a point-cloud-oriented approach that leverages normal samples, simulated anomalies, and partially observed real anomalies to model the probability density distributions of normal and anomalous data. Then, we introduce a simple Correspondence Distributions Subsampling to reduce the overlap between normal and non-normal distributions, enabling stronger dual distributions modeling. Based on these contributions, we establish a comprehensive benchmark and evaluate the proposed method extensively on Open-Industry as well as established datasets including Real3D-AD and Anomaly-ShapeNet. Benchmark results and ablation studies demonstrate the effectiveness of Open3D-AD and further reveal the potential of open-set supervised 3D anomaly detection.
format Preprint
id arxiv_https___arxiv_org_abs_2604_01171
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Open-Set Supervised 3D Anomaly Detection: An Industrial Dataset and a Generalisable Framework for Unknown Defects
Liang, Hanzhe
Zhang, Luocheng
Xia, Junyang
Zhou, HanLiang
Guo, Bingyang
Xie, Yingxi
Gao, Can
Yu, Ruiyun
Wang, Jinbao
Li, Pan
Computer Vision and Pattern Recognition
F.2.2; I.2.7
Although self-supervised 3D anomaly detection assumes that acquiring high-precision point clouds is computationally expensive, in real manufacturing scenarios it is often feasible to collect a limited number of anomalous samples. Therefore, we study open-set supervised 3D anomaly detection, where the model is trained with only normal samples and a small number of known anomalous samples, aiming to identify unknown anomalies at test time. We present Open-Industry, a high-quality industrial dataset containing 15 categories, each with five real anomaly types collected from production lines. We first adapt general open-set anomaly detection methods to accommodate 3D point cloud inputs better. Building upon this, we propose Open3D-AD, a point-cloud-oriented approach that leverages normal samples, simulated anomalies, and partially observed real anomalies to model the probability density distributions of normal and anomalous data. Then, we introduce a simple Correspondence Distributions Subsampling to reduce the overlap between normal and non-normal distributions, enabling stronger dual distributions modeling. Based on these contributions, we establish a comprehensive benchmark and evaluate the proposed method extensively on Open-Industry as well as established datasets including Real3D-AD and Anomaly-ShapeNet. Benchmark results and ablation studies demonstrate the effectiveness of Open3D-AD and further reveal the potential of open-set supervised 3D anomaly detection.
title Open-Set Supervised 3D Anomaly Detection: An Industrial Dataset and a Generalisable Framework for Unknown Defects
topic Computer Vision and Pattern Recognition
F.2.2; I.2.7
url https://arxiv.org/abs/2604.01171