← Search

Yen-Tzu Chiu

1 accepted papers

2025

Training-Free Industrial Defect Generation with Diffusion Models

ICCV 2025poster

Anomaly generation has become essential in addressing the scarcity of defective samples in industrial anomaly inspection. However, existing training-based methods fail to handle complex anomalies and multiple defects simultaneously, especially when only a single anomaly sample is available per defec…