通过保留几何中心结构重建点云，提升高精度3D异常检测效果
Taming Anomalies with Down-Up Sampling Networks: Group Center Preserving Reconstruction for 3D Anomaly Detection
- 噪声注入生成多样化训练数据，增强特征表示
- 分阶段下采样与上采样网络，实现高精度点云重建
- 在真实与合成数据集上均达当前最优性能
基于重构的方法在3D异常检测中表现优异，但在处理高精度点云时面临规模大、结构复杂等挑战。本文提出一种下-上采样网络（DUS-Net），通过保留组中心几何结构来重建高精度点云。首先引入噪声生成模块，生成带噪块以丰富训练数据并增强特征表达；随后设计下采样网络（Down-Net）从注入噪声的块中学习无异常的中心点云；再通过上采样网络（Up-Net）融合多尺度上采样特征，重建高精度点云。该方法利用组中心构建，有效保持几何结构，提供更精确的重建结果。大量实验表明，本方法在Real3D-AD和Anomaly-ShapeNet数据集上分别取得79.9%和79.5%的物体级AUROC，以及71.2%和84.7%的点级AUROC，达到当前最优（SOTA）性能。
原文摘要 · Abstract (English)
Reconstruction-based methods have demonstrated very promising results for 3D anomaly detection. However, these methods face great challenges in handling high-precision point clouds due to the large scale and complex structure. In this study, a Down-Up Sampling Network (DUS-Net) is proposed to reconstruct high-precision point clouds for 3D anomaly detection by preserving the group center geometric structure. The DUS-Net first introduces a Noise Generation module to generate noisy patches, which facilitates the diversity of training data and strengthens the feature representation for reconstruction. Then, a Down-sampling Network (Down-Net) is developed to learn an anomaly-free center point cloud from patches with noise injection. Subsequently, an Up-sampling Network (Up-Net) is designed to reconstruct high-precision point clouds by fusing multi-scale up-sampling features. Our method leverages group centers for construction, enabling the preservation of geometric structure and providing a more precise point cloud. Extensive experiments demonstrate the effectiveness of our proposed method, achieving state-of-the-art (SOTA) performance with an Object-level AUROC of 79.9% and 79.5%, and a Point-level AUROC of 71.2% and 84.7% on the Real3D-AD and Anomaly-ShapeNet datasets, respectively.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。