Towards High-resolution 3D Anomaly Detection via Group-Level Feature Contrastive Learning

Hongze Zhu, Guoyang Xie, Chengbin Hou, Tao Dai, Can GAO, Jinbao Wang, Linlin Shen

Abstract: High-resolution point clouds (HRPCD) anomaly detection (AD) plays a critical role in precision machining and high-end equipment manufacturing. Despite considerable 3D-AD methods that have been proposed recently, they still cannot meet the requirements of the HRPCD-AD task. There are several challenges: i) It is difficult to directly capture HRPCD information due to large amounts of points at the sample level; ii) The advanced transformer-based methods usually obtain anisotropic features, leading to degradation of the representation; iii) The proportion of abnormal areas is very small, which makes it difficult to characterize. To address these challenges, we propose a novel group-level feature-based network, called Group3AD, which has a significantly efficient representation ability. First, we design an Intercluster Uniformity Network (IUN) to present the mapping of different groups in the feature space as several clusters, and obtain a more uniform distribution between clusters representing different parts of the point clouds in the feature space. Then, an Intracluster Alignment Network (IAN) is designed to encourage groups within the cluster to be distributed tightly in the feature space. In addition, we propose an Adaptive Group-Center Selection~(AGCS) based on geometric information to improve the pixel density of potential anomalous regions during inference. The experimental results verify the effectiveness of our proposed Group3AD, which surpasses Reg3D-AD by the margin of 5% in terms of object-level AUROC on Real3D-AD.

Primary Subject Area: [Content] Vision and Language

Secondary Subject Area: [Experience] Multimedia Applications

Relevance To Conference: This work contributes to multimedia/multimodal processing by introducing a novel framework, Group3AD, designed for high-resolution 3D anomaly detection (AD) in industrial contexts. The framework leverages group-level feature contrastive learning to enhance the representation of 3D point clouds, which are a fundamental element in multimedia processing, particularly for capturing and analyzing spatial data. By improving the detection and localization of anomalies within complex 3D environments, Group3AD enables more accurate and efficient monitoring and quality control in industrial settings. This advancement is particularly relevant for applications that require precise analysis of physical objects, such as automated inspection systems in manufacturing, and it pushes the boundaries of how multimedia data, especially 3D content, is processed and understood. The framework's ability to handle high-resolution data and its focus on enhancing feature distribution (alignment&uniformity) within the feature space also suggest potential applications in other areas of multimedia where 3D data is utilized, such as virtual and augmented reality, 3D modeling, and computer graphics.

Submission Number: 919