Recently, 3danomalydetection, a crucial problem involving fine-grained geometry discrimination, is getting more attention. However, the lack of abundant real 3danomalydata limits the scalability of current models....
详细信息
ISBN:
(纸本)9798350353006
Recently, 3danomalydetection, a crucial problem involving fine-grained geometry discrimination, is getting more attention. However, the lack of abundant real 3danomalydata limits the scalability of current models. To enable scalable anomalydata collection, we propose a 3danomaly synthesis pipeline to adapt existing large-scale 3d models for 3danomalydetection. Specifically, we construct a synthetic dataset, i.e., anomaly-ShapeNet, based on ShapeNet. anomaly-ShapeNet consists of 1600 point cloud samples under 40 categories, which provides a rich and varied collection of data, enabling efficient training and enhancing adaptability to industrial scenarios. Meanwhile, to enable scalable representation learning for 3danomaly localization, we propose a self-supervised method, i.e., Iterative Mask Reconstruction Network (IMRNet). during training, we propose a geometry-aware sample module to preserve potentially anomalous local regions during point clouddown-sampling. Then, we randomly mask out point patches and sent the visible patches to a transformer for reconstruction-basedself-supervision. during testing, the point cloud repeatedly goes through the Mask Reconstruction Network, with each iteration's output becoming the next input. By merging and contrasting the final reconstructed point cloud with the initial input, our method successfully locates anomalies. Experiments show that IMRNet outperforms previous state-of-the-art methods, achieving 66.1% in I-AUC on our anomaly-ShapeNet dataset and 72.5% in I-AUC on Real3d-Addataset. Our benchmark will be released at https://***/Chopper-233/anomaly-ShapeNet.
暂无评论