Anomaly Detection in 3D Point Clouds using Deep Geometric Descriptors
This work addresses anomaly detection in 3D point clouds for applications like quality inspection, though it is incremental as it adapts an existing framework to a new domain.
The paper tackles unsupervised detection of geometric anomalies in 3D point clouds by adapting a student-teacher framework with a novel self-supervised pretraining strategy, achieving state-of-the-art performance on the MVTec 3D dataset and outperforming the next-best method by a large margin.
We present a new method for the unsupervised detection of geometric anomalies in high-resolution 3D point clouds. In particular, we propose an adaptation of the established student-teacher anomaly detection framework to three dimensions. A student network is trained to match the output of a pretrained teacher network on anomaly-free point clouds. When applied to test data, regression errors between the teacher and the student allow reliable localization of anomalous structures. To construct an expressive teacher network that extracts dense local geometric descriptors, we introduce a novel self-supervised pretraining strategy. The teacher is trained by reconstructing local receptive fields and does not require annotations. Extensive experiments on the comprehensive MVTec 3D Anomaly Detection dataset highlight the effectiveness of our approach, which outperforms the next-best method by a large margin. Ablation studies show that our approach meets the requirements of practical applications regarding performance, runtime, and memory consumption.