Skip to main navigation Skip to search Skip to main content

An Information-aware Reconstruction Model for Multi-category 3D Anomaly Detection

  • Hanzhe Liang
  • , Can Gao
  • , Zehai Niu
  • , Jie Zhang
  • , Jinbao Wang
  • , Linlin Shen
  • Shenzhen University
  • University of Chinese Academy of Sciences
  • University of Nottingham Ningbo China

Research output: Contribution to journal › Article › peer-review

Abstract

3D anomaly detection has recently emerged as an effective means of high-precision inspection for industrial products. However, most existing methods are typically trained in a single category-specific manner and face significant challenges in multi-category 3D anomaly detection. In this study, we propose an Information-aware Reconstruction model for Multi-category 3D Anomaly Detection (IRM3D-AD). Firstly, an Information Compression Module (ICM) is introduced to improve category specificity by removing redundant group-level features. Then, an Information-aware Mask Attention (IMA) mechanism is developed to mask key features dynamically by evaluating their information contents, thereby enhancing representation ability for all categories. Finally, an Information-aware Encoder and Decoder (IED) enforced by IMA is presented to identify anomalies from multiple categories by calculating reconstruction errors, which is optimized using information bottleneck constraints to maintain specificity and generalization. Experimental results demonstrate that our method outperforms both single-category and multicategory methods, achieving an average object-level AUROC improvement of 5.7%, 3.3%, and 6.3% on Anomaly-ShapeNet, Real3D-AD, and MulSen-AD, respectively.

Original languageEnglish
JournalIEEE Transactions on Artificial Intelligence
DOIs
Publication statusAccepted/In press - 2026

Keywords

  • 3D point cloud
  • Anomaly detection
  • information bottleneck
  • information-aware mask attention
  • multi-category detection

Fingerprint

Dive into the research topics of 'An Information-aware Reconstruction Model for Multi-category 3D Anomaly Detection'. Together they form a unique fingerprint.

Cite this