MTDiff: Visual anomaly detection with multi-scale diffusion models

Advancements in computer vision have fueled rapid developments in unsupervised anomaly detection, but current methods often encounter limitations when addressing anomalies with varying scales, and the intricate pipelines that require significant tuning efforts further hinder the usability. In this work, we propose MTDiff, a novel anomaly detection method comprising diffusion models built on different scales. In essence, the constructed scale-specific branches and their incorporation can enhance the pattern coverage, thus improving performance. MTDiff involves two parts: reconstruction that repairs the anomalous region to pseudo-normal, and detection that carefully compares and localizes the anomalies. Instead of the typical forward process of diffusion, we construct a partial Markov chain to improve the reconstruction quality. During the discrimination, we construct a simple but effective detector that operates on feature-level to better utilize the rich contextual information. MTDiff comes with a concise training pipeline, with optimized diffusion iterations ensuring the efficiency. Sufficient experiments reveal that it outperforms the state-of-the-art approaches, showing superior stability and robustness in both image- and pixel-level anomaly detection. The related code is available at https://github.com/vergilben/MTDiff.