用两步实现高效3D点云异常检测，速度比现有方法快80倍。
Two Steps Are All You Need: Efficient 3D Point Cloud Anomaly Detection with Consistency Models
- 基于一致性学习，仅需1-2次网络推理即可生成无异常几何结构。
- 在Anomaly-ShapeNet上达到76.20% I-AUROC，Real3DAD上达72.80% I-AUROC。
- 适合部署在无人机、工业摄像头等边缘设备，低延迟、低资源消耗。
扩散模型正迅速重塑点云数据的3D异常检测。随着3D传感在现代制造中的普及，高通量质量保证与过程控制亟需可靠的异常检测。然而，在资源受限、延迟敏感的系统中实际部署仍受限制。现有方法常计算开销大或在复杂未遮挡区域不可靠，且扩散流程固有地受迭代去噪瓶颈制约。本文通过一致性学习重构异常检测范式，实现一次或两次网络评估即直接预测无异常几何。我们提出一种新型混合损失函数，显式约束重建向清洁数据对齐。该设计显著降低推理成本，无需GPU加速即可实现比当前最先进方法快80倍的运行速度，同时保持强检测性能。在Anomaly-ShapeNet上达到76.20% I-AUROC，Real3DAD上达72.80% I-AUROC，支持在无人机、智能工业相机等边缘设备上实现高效、低延迟的异常检测。
原文摘要 · Abstract (English)
Diffusion models are rapidly redefining 3D anomaly detection in point cloud data. As 3D sensing becomes integral to modern manufacturing, reliable anomaly detection is essential for high-throughput quality assurance and process control. Yet practical deployment on resource-constrained, latency-critical systems remains limited. Existing methods are often computationally prohibitive or unreliable in complex, unmasked regions, and diffusion pipelines are inherently bottlenecked by iterative denoising. In this work, we address this bottleneck by reformulating reconstructionbased anomaly detection through consistency learning, enabling direct prediction of anomaly-free geometry in one or two network evaluations. We further introduce a novel hybrid loss formulation that explicitly enforces reconstruction toward clean data. This design substantially reduces inference cost, achieving up to 80x faster runtime than the current state-of-the-art method, without GPU acceleration, while preserving strong detection performance. It outperforms R3D-AD on Anomaly-ShapeNet with 76.20% I-AUROC and remains competitive on Real3DAD with 72.80% I-AUROC, enabling efficient, low-latency anomaly detection on resource-constrained platforms, including drones, smart industrial cameras, and other edge devices.
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。