Unsupervised anomaly detection methods are at the forefront of industrial
anomaly detection efforts and have made notable progress. Previous work
primarily used 2D information as input, but multi-modal industrial anomaly
detection based on 3D point clouds and RGB images is just beginning to emerge.
The regular approach involves utilizing large pre-trained models for feature
representation and storing them in memory banks. However, the above methods
require a longer inference time and higher memory usage, which cannot meet the
real-time requirements of the industry. To overcome these issues, we propose a
lightweight dual-branch reconstruction network(DBRN) based on RGB-D input,
learning the decision boundary between normal and abnormal examples. The
requirement for alignment between the two modalities is eliminated by using
depth maps instead of point cloud input. Furthermore, we introduce an
importance scoring module in the discriminative network to assist in fusing
features from these two modalities, thereby obtaining a comprehensive
discriminative result. DBRN achieves 92.8% AUROC with high inference efficiency
on the MVTec 3D-AD dataset without large pre-trained models and memory banks.

基于 RGB-D 输入，我们提出了一种轻量级的双分支重建网络 (DBRN)，通过学习正常和异常样本之间的决策边界，使用深度图而不是点云输入来消除两种模态之间的对齐要求，并引入了一个重要性评分模块来辅助融合这两种模态的特征，从而在 MVTec 3D-AD 数据集上实现了 92.8% 的 AUROC，并具有很高的推理效率，无需使用大型预训练模型和记忆库。