SplatPose+: Real-time Image-Based Pose-Agnostic 3D Anomaly Detection

TL;DR

SplatPose+ introduces a real-time, pose-agnostic 3D anomaly detection method combining SfM and 3D Gaussian Splatting, achieving state-of-the-art results in industrial quality control applications.

Contribution

The paper presents SplatPose+, a novel hybrid approach that enables real-time pose-agnostic 3D anomaly detection using SfM and 3D Gaussian Splatting, improving speed and accuracy over prior methods.

Findings

Achieved new state-of-the-art on MAD-SIM dataset.

Real-time inference speeds suitable for industrial use.

Faster training compared to previous SplatPose method.

Abstract

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.