Large-Scale Universal Defect Generation: Foundation Models and Datasets

ArXi:2604.08915v1 Announce Type: cross Existing defect/anomaly generation methods often rely on few-shot learning, which overfits to specific defect categories due to the lack of large-scale paired defect editing data. This issue is aggravated by substantial variations in defect scale and morphology, resulting in limited generalization, degraded realism, and category consistency. We address these challenges by