A new three-sensor industrial anomaly detection dataset and benchmark shows that fusing RGB, infrared, and point cloud data improves object-level detection to 96.1% AUROC over single-sensor baselines.
The mvtec 3d-ad dataset for unsupervised 3d anomaly detec- tion and localization
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Multi-Sensor Object Anomaly Detection: Unifying Appearance, Geometry, and Internal Properties
A new three-sensor industrial anomaly detection dataset and benchmark shows that fusing RGB, infrared, and point cloud data improves object-level detection to 96.1% AUROC over single-sensor baselines.