2D-based Industrial Anomaly Detection has been widely discussed, however, multimodal industrial anomaly detection based on 3D point clouds and RGB images still has many untouched fields. Existing multimodal industrial anomaly detection methods directly concatenate the multimodal features, which leads to a strong disturbance between features and harms the detection performance. In this paper, we propose Multi-3D-Memory (M3DM), a novel multimodal anomaly detection method with hybrid fusion scheme: firstly, we design an unsupervised feature fusion with patch-wise contrastive learning to encourage the interaction of different modal features; secondly, we use a decision layer fusion with multiple memory banks to avoid loss of information and additional novelty classifiers to make the final decision. We further propose a point feature alignment operation to better align the point cloud and RGB features. Extensive experiments show that our multimodal industrial anomaly detection model outperforms the state-of-the-art (SOTA) methods on both detection and segmentation precision on MVTec-3D AD dataset. Code is available at https://github.com/nomewang/M3DM.

翻译：基于2D图像的工业异常检测已被广泛讨论，但基于3D点云与RGB图像的多模态工业异常检测仍存在许多未探索领域。现有方法通常直接拼接多模态特征，导致特征间强烈干扰并损害检测性能。本文提出一种具有混合融合方案的新型多模态异常检测方法——Multi-3D-Memory (M3DM)：首先，设计基于补丁级对比学习的无监督特征融合，以促进不同模态特征间的交互；其次，采用基于多记忆库的决策层融合，避免信息丢失，并引入额外新颖性分类器进行最终决策。此外，我们提出点特征对齐操作以更好地对齐点云与RGB特征。大量实验表明，所提多模态工业异常检测模型在MVTec-3D AD数据集上的检测与分割精度均优于当前最优（SOTA）方法。代码已开源：https://github.com/nomewang/M3DM。