AnomalyControl injects cross-modal semantic features from a text and image reference into a frozen diffusion model to synthesize controllable, realistic industrial defects, slightly outperforming prior anomaly synthesis methods on MVTec AD, MPDD, and ViSA.
The mvtec anomaly detection dataset: a comprehensive real-world dataset for unsupervised anomaly detection
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
-
AnomalyControl: Learning Cross-modal Semantic Features for Controllable Anomaly Synthesis
AnomalyControl injects cross-modal semantic features from a text and image reference into a frozen diffusion model to synthesize controllable, realistic industrial defects, slightly outperforming prior anomaly synthesis methods on MVTec AD, MPDD, and ViSA.