A background-aware diffusion loss and mask refinement generate synthetic industrial defects that preserve background structure and improve anomaly detection on MVTec-AD and MVTec-Loco.
Beyond dents and scratches: Logical constraints in unsupervised anomaly detection and localization
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Background-Aware Defect Generation for Robust Industrial Anomaly Detection
A background-aware diffusion loss and mask refinement generate synthetic industrial defects that preserve background structure and improve anomaly detection on MVTec-AD and MVTec-Loco.