实时检测工业品3D异常，无需预知拍摄角度。
SplatPose+: Real-time Image-Based Pose-Agnostic 3D Anomaly Detection
- 结合SfM定位与3DGS建模，实现跨视角图像对比。
- 在MAD-SIM数据集上达到新最佳性能，推理速度达实时要求。
- 适合高速产线质检，兼顾精度与效率，优于现有方法。
基于图像的无姿态依赖3D异常检测是工业质量控制中的重要任务，旨在通过一组无异常参考图像，从任意未知视角的待测图像中发现缺陷。难点在于查询视角（即姿态）未知且可能不同于参考视角。现有方法如OmniposeAD和SplatPose通过在查询视角合成伪参考图像进行像素级对比，但均无法实现实时推理，难以满足大规模生产需求。为此，本文提出SplatPose+，采用SfM模型进行定位，结合3D高斯点云渲染（3DGS）实现新视角合成。尽管需额外计算SfM模型，但该流程实现了实时推理，训练速度更快。在无姿态异常检测基准测试中，SplatPose+于Multi-Pose Anomaly Detection (MAD-SIM) 数据集上取得当前最优性能。
原文摘要 · Abstract (English)
Image-based Pose-Agnostic 3D Anomaly Detection is an important task that has emerged in industrial quality control. This task seeks to find anomalies from query images of a tested object given a set of reference images of an anomaly-free object. The challenge is that the query views (a.k.a poses) are unknown and can be different from the reference views. Currently, new methods such as OmniposeAD and SplatPose have emerged to bridge the gap by synthesizing pseudo reference images at the query views for pixel-to-pixel comparison. However, none of these methods can infer in real-time, which is critical in industrial quality control for massive production. For this reason, we propose SplatPose+, which employs a hybrid representation consisting of a Structure from Motion (SfM) model for localization and a 3D Gaussian Splatting (3DGS) model for Novel View Synthesis. Although our proposed pipeline requires the computation of an additional SfM model, it offers real-time inference speeds and faster training compared to SplatPose. Quality-wise, we achieved a new SOTA on the Pose-agnostic Anomaly Detection benchmark with the Multi-Pose Anomaly Detection (MAD-SIM) dataset.
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。