AI RESEARCH
A Semantically Disentangled Unified Model for Multi-category 3D Anomaly Detection
arXiv CS.CV
•
ArXi:2603.25159v1 Announce Type: new 3D anomaly detection targets the detection and localization of defects in 3D point clouds trained solely on normal data. While a unified model improves scalability by learning across multiple categories, it often suffers from Inter-Category Entanglement (ICE)-where latent features from different categories overlap, causing the model to adopt incorrect semantic priors during reconstruction and ultimately yielding unreliable anomaly scores.