DAS3D: Dual-modality Anomaly Synthesis for 3D Anomaly Detection
This addresses the challenge of multi-modality anomaly detection in industrial settings, offering an incremental improvement over existing methods.
The paper tackles the problem of 3D anomaly detection by proposing a dual-modality augmentation method for synthesizing anomalies, combined with a reconstruction-based network, achieving state-of-the-art detection precision and competitive segmentation on MVTec 3D-AD and Eyescandies datasets.
Synthesizing anomaly samples has proven to be an effective strategy for self-supervised 2D industrial anomaly detection. However, this approach has been rarely explored in multi-modality anomaly detection, particularly involving 3D and RGB images. In this paper, we propose a novel dual-modality augmentation method for 3D anomaly synthesis, which is simple and capable of mimicking the characteristics of 3D defects. Incorporating with our anomaly synthesis method, we introduce a reconstruction-based discriminative anomaly detection network, in which a dual-modal discriminator is employed to fuse the original and reconstructed embedding of two modalities for anomaly detection. Additionally, we design an augmentation dropout mechanism to enhance the generalizability of the discriminator. Extensive experiments show that our method outperforms the state-of-the-art methods on detection precision and achieves competitive segmentation performance on both MVTec 3D-AD and Eyescandies datasets.