DefectFill: Realistic Defect Generation with Inpainting Diffusion Model for Visual Inspection

Developing effective visual inspection models remains challenging due to the scarcity of defect data, especially in new or low-defect-rate manufacturing processes. While recent approaches have attempted to generate defect images using image generation models, producing highly realistic defects remains difficult. In this paper, we propose DefectFill, a novel method for realistic defect generation that requires only a few reference defect images. DefectFill leverages a fine-tuned inpainting diffusion model, optimized with our custom loss functions that incorporate defect, object, and cross-attention terms. This approach enables the inpainting diffusion model to precisely capture detailed, localized defect features and seamlessly blend them into defect-free objects. Additionally, we introduce the Low-Fidelity Selection method to further enhance the quality of the generated defect samples. Experiments demonstrate that DefectFill can generate high-quality defect images, and visual inspection models trained on these images achieve state-of-the-art performance on the MVTec AD dataset.