回归点云：探索点-语言模型用于零样本3D异常检测
Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection
该论文提出直接利用点云与文本对齐的预训练点-语言模型进行零样本3D异常检测，避免2D渲染的信息损失，其多粒度图像块特征与文本对齐、几何描述子增强的策略可复用于其他3D下游任务（如3D分割、定位）中的跨模态表征学习。
原文依据 we revisit intrinsic 3D representations and explore the potential of pre-trained Point-Language Models (PLMs) for ZS 3D anomaly detection
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论零样本（ZS）3D异常检测对于可靠的工业检测至关重要，因为它无需任何目标类别的训练数据即可检测和定位缺陷。现有方法将3D点云渲染为2D图像，并利用预训练的视觉-语言模型（VLM）进行异常检测。然而，此类策略不可避免地丢弃了几何细节，并对局部异常表现出有限的敏感性。本文重新审视内在的3D表示，并探索预训练的点-语言模型（PLM）在零样本3D异常检测中的潜力。我们提出了BTP（回归点云），一种有效对齐3D点云与文本嵌入的新框架。具体而言，BTP将多粒度图像块特征与文本表示对齐以进行局部异常检测，同时引入几何描述子以增强对结构异常的敏感性。此外，我们引入了一种联合表征学习策略，利用辅助点云数据来提高鲁棒性并丰富异常语义。在Real3D-AD和Anomaly-ShapeNet上的大量实验表明，BTP在零样本3D异常检测中取得了优越的性能。
英文原文摘要 1205 字符
Zero-shot (ZS) 3D anomaly detection is crucial for reliable industrial inspection, as it enables detecting and localizing defects without requiring any target-category training data. Existing approaches render 3D point clouds into 2D images and leverage pre-trained Vision-Language Models (VLMs) for anomaly detection. However, such strategies inevitably discard geometric details and exhibit limited sensitivity to local anomalies. In this paper, we revisit intrinsic 3D representations and explore the potential of pre-trained Point-Language Models (PLMs) for ZS 3D anomaly detection. We propose BTP (Back To Point), a novel framework that effectively aligns 3D point cloud and textual embeddings. Specifically, BTP aligns multi-granularity patch features with textual representations for localized anomaly detection, while incorporating geometric descriptors to enhance sensitivity to structural anomalies. Furthermore, we introduce a joint representation learning strategy that leverages auxiliary point cloud data to improve robustness and enrich anomaly semantics. Extensive experiments on Real3D-AD and Anomaly-ShapeNet demonstrate that BTP achieves superior performance in ZS 3D anomaly detection.