Multi-View Reconstruction with Global Context for 3D Anomaly Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sun, Yihan, Cheng, Yuqi, Cao, Yunkang, Zhang, Yuxin, Shen, Weiming
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908470905667584
author Sun, Yihan
Cheng, Yuqi
Cao, Yunkang
Zhang, Yuxin
Shen, Weiming
author_facet Sun, Yihan
Cheng, Yuqi
Cao, Yunkang
Zhang, Yuxin
Shen, Weiming
contents 3D anomaly detection is critical in industrial quality inspection. While existing methods achieve notable progress, their performance degrades in high-precision 3D anomaly detection due to insufficient global information. To address this, we propose Multi-View Reconstruction (MVR), a method that losslessly converts high-resolution point clouds into multi-view images and employs a reconstruction-based anomaly detection framework to enhance global information learning. Extensive experiments demonstrate the effectiveness of MVR, achieving 89.6\% object-wise AU-ROC and 95.7\% point-wise AU-ROC on the Real3D-AD benchmark.
format Preprint
id arxiv_https___arxiv_org_abs_2507_21555
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Multi-View Reconstruction with Global Context for 3D Anomaly Detection
Sun, Yihan
Cheng, Yuqi
Cao, Yunkang
Zhang, Yuxin
Shen, Weiming
Computer Vision and Pattern Recognition
3D anomaly detection is critical in industrial quality inspection. While existing methods achieve notable progress, their performance degrades in high-precision 3D anomaly detection due to insufficient global information. To address this, we propose Multi-View Reconstruction (MVR), a method that losslessly converts high-resolution point clouds into multi-view images and employs a reconstruction-based anomaly detection framework to enhance global information learning. Extensive experiments demonstrate the effectiveness of MVR, achieving 89.6\% object-wise AU-ROC and 95.7\% point-wise AU-ROC on the Real3D-AD benchmark.
title Multi-View Reconstruction with Global Context for 3D Anomaly Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.21555