Background-Aware Defect Generation for Robust Industrial Anomaly Detection

TL;DR

This paper introduces a background-aware defect generation method that improves the realism and contextual accuracy of synthetic anomalies, enhancing industrial anomaly detection performance.

Contribution

It proposes a novel disentanglement-based framework that separates background and defect synthesis, ensuring structural integrity and realistic defect generation.

Findings

Outperforms existing methods in defect generation quality.

Achieves superior anomaly detection accuracy on benchmarks.

Maintains background fidelity during defect synthesis.

Abstract

Detecting anomalies in industrial settings is challenging due to the scarcity of labeled anomalous data. Generative models can mitigate this issue by synthesizing realistic defect samples, but existing approaches often fail to model the crucial interplay between defects and their background. This oversight leads to unrealistic anomalies, especially in scenarios where contextual consistency is essential (i.e., logical anomaly). To address this, we propose a novel background-aware defect generation framework, where the background influences defect denoising without affecting the background itself by ensuring realistic synthesis while preserving structural integrity. Our method leverages a disentanglement loss to separate the background' s denoising process from the defect, enabling controlled defect synthesis through DDIM Inversion. We theoretically demonstrate that our approach maintains background fidelity while generating contextually accurate defects. Extensive experiments on MVTec AD and MVTec Loco benchmarks validate our mehtod's superiority over existing techniques in both defect generation quality and anomaly detection performance.