Cheating Depth: Enhancing 3D Surface Anomaly Detection via Depth Simulation. (arXiv:2311.01117v1 [cs.CV])

RGB-based surface anomaly detection methods have advanced significantly.
However, certain surface anomalies remain practically invisible in RGB alone,
necessitating the incorporation of 3D information. Existing approaches that
employ point-cloud backbones suffer from suboptimal representations and reduced
applicability due to slow processing. Re-training RGB backbones, designed for
faster dense input processing, on industrial depth datasets is hindered by the
limited availability of sufficiently large datasets. We make several
contributions to address these challenges. (i) We propose a novel Depth-Aware
Discrete Autoencoder …

advanced anomaly anomaly detection arxiv cheating cloud detection detection methods faster information point-cloud processing simulation surface training