Bookmark Saya

arXiv Open Access 2025

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

Yihan Sun Yuqi Cheng Yunkang Cao Yuxin Zhang Weiming Shen
Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

cs.CV

Penulis (5)

Y

Yihan Sun

Y

Yuqi Cheng

Y

Yunkang Cao

Y

Yuxin Zhang

W

Weiming Shen

Format Sitasi

APA MLA BibTeX
Sun, Y., Cheng, Y., Cao, Y., Zhang, Y., Shen, W. (2025). Multi-View Reconstruction with Global Context for 3D Anomaly Detection. https://arxiv.org/abs/2507.21555

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2025
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓