Oct 2026· International Conference on Computer Vision, Robotics and Automation Engineering· Vol 14353, pp. 1435306 - 1435306-6· 0 citations· 10 references
Engineering
TL;DR
A unified framework to address gaps in memory-bank-based 3D point cloud anomaly detection via two integrated components: Normal-Aware Registration Features (NARF), which augments the RANSAC--ICP pipeline to extract per-point orientations with negligible overhead, and Geometry-Aware Coreset Sampling (GACS), which prioritizes high-curvature regions using curvature- and normal-variation-weighted sampling.
Abstract
Memory-bank-based 3D point cloud anomaly detection identifies defects via nearest-neighbor retrieval of nominal features. However, current methods often neglect surface normals and suffer from inadequate coverage of complex geometries due to random coreset initialization. We propose a unified framework to address these gaps via two integrated components: Normal-Aware Registration Features (NARF), which augments the RANSAC--ICP pipeline to extract per-point orientations with negligible overhead, and Geometry-Aware Coreset Sampling (GACS), which prioritizes high-curvature regions using curvature- and normal-variation-weighted sampling. By fusing coordinate, semantic (PointMAE), and angular-deviation streams through rank-normalization, our approach achieves 84.4% O-AUROC on the Real3D-AD benchmark, delivering state-of-the-art performance with enhanced geometric discriminability.
Unsupervised 3D point-cloud anomaly detection trains exclusively on normal samples and must identify anomalous objects and localize anomalous regions at test time. Although high-resolution, complete point clouds encode fine-grained geometric detail, defects typically affect only a small fraction of the object surface;...
Cai-Chen Gao, Peng Guan, Zheng-Yu Xue et al.· Engineering Research Express· 0 citations
To address missed detections of distant sparse objects in LiDAR 3D detection and inference latency on edge devices, we propose GD-Pillars, a lightweight algorithm. First, a Geometry and Density-Aware Pillar Feature Encoding (GD-PFE) network enhances local geometric descriptions and compensates for sparse target feature...
Yue Zhang, Qing-Hua Zeng, Fang-Dong Li et al.· Journal of Physics, Conferen...· 0 citations
Detecting and localizing 3D point-cloud defects is essential for industrial inspection. However, existing methods often suffer from imprecise localization due to the lack of anomaly supervision and reliance on single-granularity representations. To address these limitations, we propose Anomaly Type-Aware 3D Anomaly Det...
3-D point cloud (PC) change detection is an essential task in urban monitoring. Recent raw-point frameworks preserve native 3-D geometric information more effectively than projection-based or voxelization-based pipelines. However, robust change detection in bitemporal urban scenes remains challenging because irregular...
Jin-Feng Xu, Chen-Fei Hou, Heng-Lai Wei et al.· IEEE Geoscience and Remote S...· 1 citation
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 co...
Yu-Tong Gu, Ying-Xi Xie, Ke-Jin Huang et al.· 0 citations
Multi-view anomaly detection (MvAD) detects defects by exploiting complementary observations from multiple camera viewpoints. The central challenge is to fuse views with sufficient geometric awareness while remaining scalable to multi-class industrial settings. Existing methods typically fall into two extremes: voxel-b...
Shang-Fu Chen, Jhih-Ciang Wu, Kuan-Chuan Peng et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
