D3R-Net: Dual-Domain Denoising Reconstruction Network for Robust Industrial Anomaly Detection

TL;DR

D3R-Net introduces a dual-domain denoising reconstruction framework with frequency-aware regularization, significantly improving subtle defect detection in industrial anomaly detection tasks while maintaining efficiency.

Contribution

The paper proposes D3R-Net, a novel unsupervised anomaly detection model combining spatial and frequency domain losses, enhancing defect localization accuracy over existing methods.

Findings

FFT loss improves localization consistency (PRO AUC from 0.603 to 0.687)

Average pixel ROC AUC increases from 0.733 to 0.751

Achieves roughly 20 FPS on a single GPU

Abstract

Unsupervised anomaly detection (UAD) is a key ingredient of automated visual inspection in modern manufacturing. The reconstruction-based methods appeal because they have basic architectural design and they process data quickly but they produce oversmoothed results for high-frequency details. As a result, subtle defects are partially reconstructed rather than highlighted, which limits segmentation accuracy. We build on this line of work and introduce D3R-Net, a Dual-Domain Denoising Reconstruction framework that couples a self-supervised 'healing' task with frequency-aware regularization. During training, the network receives synthetically corrupted normal images and is asked to reconstruct the clean targets, which prevents trivial identity mapping and pushes the model to learn the manifold of defect-free textures. In addition to the spatial mean squared error, we employ a Fast Fourier Transform (FFT) magnitude loss that encourages consistency in the frequency domain. The implementation also allows an optional structural similarity (SSIM) term, which we study in an ablation. On the MVTec AD Hazelnut benchmark, D3R-Net with the FFT loss improves localization consistency over a spatial-only baseline: PRO AUC increases from 0.603 to 0.687, while image-level ROC AUC remains robust. Evaluated across fifteen MVTec categories, the FFT variant raises the average pixel ROC AUC from 0.733 to 0.751 and PRO AUC from 0.417 to 0.468 compared to the MSE-only baseline, at roughly 20 FPS on a single GPU. The network is trained from scratch and uses a lightweight convolutional autoencoder backbone, providing a practical alternative to heavy pre-trained feature embedding methods.