发表机构
Shenzhen University WeBank Institute of Finance, Shenzhen University; School of Computer Science, Wuhan University; Shenzhen Audencia Financial Technology Institute, Shenzhen University; Mohamed bin Zayed University of Artificial Intelligence; School of Artificial Intelligence, Shenzhen University（深圳大学微众银行金融科技学院; 武汉大学计算机学院; 深圳大学深圳南特金融科技学院; 穆罕默德·本·扎耶德人工智能大学; 深圳大学人工智能学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对边缘低分辨率传感器导致的点云稀疏问题，提出PC$^2$-AD上采样框架，通过候选生成、过滤与补偿，提升3D异常检测性能，实验验证了其有效性。
AI 中文摘要
在边缘部署中使用的低成本、低分辨率传感器可能产生比正常训练数据稀疏得多的测试点云。这种训练-测试采样分辨率差距改变了3D异常检测器可用的局部几何信息。我们提出了PC$^2$-AD，一个点云上采样框架，在下游检测之前补偿稀疏的测试输入。目标域候选生成（TCG）将预训练的上采样器适应于正常训练几何，并生成密集的候选池。几何感知候选过滤（GACF）根据几何间距和空间覆盖选择候选。正态性保持点补偿（NPPC）通过比较候选正态性分数与其输入锚点的分数来细化选择。选定的点与未改变的输入点结合，并由现有检测器处理。在两种Anomaly-ShapeNet设置和Real3D-AD上使用六个检测器的实验显示，在每个Anomaly-ShapeNet设置中，所有六个检测器的对象级和点级AUROC平均值均有提升，在Real3D-AD上有四个检测器提升。这些结果支持点云补偿作为一种输入级方法，在低分辨率感知条件下改进3D异常检测。代码在此https URL公开可用。
英文摘要
Low-cost and low-resolution sensors used in edge deployments can produce test point clouds that are substantially sparser than the normal training data. This train-test sampling-resolution gap changes the local geometry available to a 3D anomaly detector. We propose PC$^2$-AD, a point cloud upsampling framework that compensates sparse test inputs before downstream detection. Target Domain Candidate Generation (TCG) adapts a pretrained upsampler to normal training geometry and generates a dense candidate pool. Geometry-Aware Candidate Filtering (GACF) selects candidates according to geometric spacing and spatial coverage. Normality-Preserving Point Compensation (NPPC) refines the selection by comparing candidate normality scores with those of their input anchors. The selected points are combined with the unchanged input points and processed by the existing detector. Experiments with six detectors on two Anomaly-ShapeNet settings and Real3D-AD show improvements in the mean of object-level and point-level AUROC for all six detectors in each Anomaly-ShapeNet setting and four on Real3D-AD. These results support point cloud compensation as an input-level approach to improving 3D anomaly detection under low-resolution sensing conditions. Code is publicly available at https://github.com/gyutong406-commits/PC2-AD.
Comments17 pages, including 6 pages of supplementary material. Code: https://github.com/gyutong406-commits/PC2-AD
