Organizations: Shenzhen University WeBank Institute of Finance, Shenzhen University, Shenzhen 518060, China · School of Computer Science, Wuhan University, Wuhan 430072, China · Shenzhen Audencia Financial Technology Institute, Shenzhen University, Shenzhen 518060, China · Mohamed bin Zayed University of Artificial Intelligence, Masdar City, Abu Dhabi, UAE · School of Artificial Intelligence, Shenzhen University, Shenzhen, Guangdong, China
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 PC2-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.
Figures & tables
Fig. 1: Motivation for client-side resolution compensation. (a) O-AUROC and P-AUROC under different test resolutions, with the training resolution fixed at 0.8 . The dashed line indicates the aligned setting. (b) Low-resolution sensor inputs are compensated on the client before being passed to the 3D anomaly detection model.
Fig. 2: Overview of PC2 -AD. TCG adapts a pretrained distance estimator through TDA and uses it for candidate generation (CG). GACF filters the candidates by anchor distance and spatial coverage. NPPC trains the patch encoder through CNP and MSCF, constructs a normal feature bank, and uses it for same-anchor replacement. The selected points are combined with the unchanged input points before downstream anomaly detection.
Fig. 3: Qualitative results of PC2 -AD on Anomaly-ShapeNet and Real3D-AD.
Fig. 5: Parameter sensitivity of PC2 -AD. Avg. AUROC and Avg. AUPRC denote the averages of O-AUROC and P-AUROC, and of O-AUPRC and P-AUPRC, respectively. FPS denotes generation speed in samples per second. Hollow black circles mark the default configuration, and dotted horizontal lines indicate the corresponding default results.
Point cloud anomaly detection identifies and localizes unusual 3D geometry or surface defects, often in industrial inspection with few labeled failures.
School of Computer Science, Wuhan University, Wuhan 430072, Hubei, China · Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen 518060, Guangdong, China · School of Information and Software Engineering, East China Jiaotong University, Nanchang 330013, Jiangxi, China +1
University of British Columbia, Vancouver, V6T 1Z4 BC, Canada · Vancouver Prostate Centre, M.H. Mohseni Institute of Urologic Sciences, Vancouver, V6H 3ZB BC, Canada · Department of Urologic Sciences, The University of British Columbia, Vancouver, V5Z 1M9 BC, Canada