论文标题
返回该功能：经典的3D功能是（几乎）3D异常检测所需的所有功能
Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection
论文作者
论文摘要
尽管图像异常检测和分割方面取得了重大进展，但很少有方法使用3D信息。我们利用最近引入的3D异常检测数据集来评估使用3D信息是否丢失了机会。首先，我们提出了一个令人惊讶的发现：仅标准颜色方法优于明确设计用于利用3D信息的所有当前方法。这是违反直觉的，因为即使对数据集的简单检查也表明，只有颜色的方法不足以用于包含几何异常的图像。这激发了一个问题：如何有效地使用3D信息？我们研究了一系列形状表示，包括手工制作和深度学习；我们证明旋转不变性在性能中起主要作用。我们发现了一种简单的仅3D方法，该方法在不使用深度学习，外部预训练数据集或颜色信息的同时击败了所有最新方法。由于仅3D方法无法检测到颜色和纹理异常，因此我们将其与基于颜色的功能相结合，明显优于先前的最新动态。我们的方法被称为BTF（返回功能）实现像素的Rocauc：99.3％和Pro：MVTEC 3D-AD上的96.4％。
Despite significant advances in image anomaly detection and segmentation, few methods use 3D information. We utilize a recently introduced 3D anomaly detection dataset to evaluate whether or not using 3D information is a lost opportunity. First, we present a surprising finding: standard color-only methods outperform all current methods that are explicitly designed to exploit 3D information. This is counter-intuitive as even a simple inspection of the dataset shows that color-only methods are insufficient for images containing geometric anomalies. This motivates the question: how can anomaly detection methods effectively use 3D information? We investigate a range of shape representations including hand-crafted and deep-learning-based; we demonstrate that rotation invariance plays the leading role in the performance. We uncover a simple 3D-only method that beats all recent approaches while not using deep learning, external pre-training datasets, or color information. As the 3D-only method cannot detect color and texture anomalies, we combine it with color-based features, significantly outperforming previous state-of-the-art. Our method, dubbed BTF (Back to the Feature) achieves pixel-wise ROCAUC: 99.3% and PRO: 96.4% on MVTec 3D-AD.
