Traditional reconstruction-based visual anomaly detection methods struggle to achieve competitive performance. This is primarily because most existing approaches are unable to precisely reconstruct anomalous inputs resulting in restored pattern that diverge from the original image. Moreover, methods often fail to conduct a robust comparison between the reconstructed and input images. In this paper, we propose Denoising Diffusion Anomaly Detection (DDAD) whereby a generic diffusion model is first trained only on nominal data. During inference, the reverse process is conditioned on the unperturbed input image by correcting the predicted noise at each denoising step. This novel mechanism accurately reconstructs anomalous regions while preserving the in-distribution patterns of the image. Finally, the input image and its reconstruction are compared via pixel-wise and feature-wise matching. Additionally, to enhance the effectiveness of the feature-wise comparison, we introduce a domain adaptation method that leverages nearly identical generated examples from our conditioned denoising process to fine-tune the pre-trained feature extractor. We validate the efficacy of DDAD on various datasets, including MVTec and VisA benchmarks, achieving state-of-the-art results with 99.8% and 98.9% image-level AUROC, respectively. Source code is available at GitHub.