3DKeyAD: High-Resolution 3D Point Cloud Anomaly Detection via Keypoint-Guided Point Clustering

TL;DR

This paper presents a novel high-resolution 3D point cloud anomaly detection method that leverages keypoint-guided clustering and multi-prototype alignment for precise localization, outperforming existing approaches.

Contribution

It introduces a registration-based framework with keypoint-guided clustering for improved 3D anomaly detection and localization in high-resolution point clouds.

Findings

Achieves state-of-the-art results on Real3D-AD benchmark.

Effective in both object-level and point-level anomaly detection.

Operates efficiently using only raw features.

Abstract

High-resolution 3D point clouds are highly effective for detecting subtle structural anomalies in industrial inspection. However, their dense and irregular nature imposes significant challenges, including high computational cost, sensitivity to spatial misalignment, and difficulty in capturing localized structural differences. This paper introduces a registration-based anomaly detection framework that combines multi-prototype alignment with cluster-wise discrepancy analysis to enable precise 3D anomaly localization. Specifically, each test sample is first registered to multiple normal prototypes to enable direct structural comparison. To evaluate anomalies at a local level, clustering is performed over the point cloud, and similarity is computed between features from the test sample and the prototypes within each cluster. Rather than selecting cluster centroids randomly, a keypoint-guided strategy is employed, where geometrically informative points are chosen as centroids. This ensures that clusters are centered on feature-rich regions, enabling more meaningful and stable distance-based comparisons. Extensive experiments on the Real3D-AD benchmark demonstrate that the proposed method achieves state-of-the-art performance in both object-level and point-level anomaly detection, even using only raw features.