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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Yizhe, Hu, Yan Song, Chen, Yuhao, Zelek, John
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914974197088256
author Liu, Yizhe
Hu, Yan Song
Chen, Yuhao
Zelek, John
author_facet Liu, Yizhe
Hu, Yan Song
Chen, Yuhao
Zelek, John
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_12080
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SplatPose+: Real-time Image-Based Pose-Agnostic 3D Anomaly Detection
Liu, Yizhe
Hu, Yan Song
Chen, Yuhao
Zelek, John
Computer Vision and Pattern Recognition
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.
title SplatPose+: Real-time Image-Based Pose-Agnostic 3D Anomaly Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.12080