IAENet fuses 2D and 3D anomaly scores with a learned importance-aware weighting and a margin-based selector loss, achieving state-of-the-art point-level localization on MVTec 3D-AD.
3d-adcs: Untrained 3d anomaly detectionforcomplexmanufacturingsurfaces
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
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
IAENet: An Importance-Aware Ensemble Model for 3D Point Cloud-Based Anomaly Detection
IAENet fuses 2D and 3D anomaly scores with a learned importance-aware weighting and a margin-based selector loss, achieving state-of-the-art point-level localization on MVTec 3D-AD.