EUVIMEDEUVIMED entdecken
Crossref

Multimodal Industrial Anomaly Detection via Geometric Prior

Min Li, Jinghui He, Gang Li, Jiachen Li, Jin Wan, Delong Han

IEEE Transactions on Circuits and Systems for Video Technology · 2026-03 · 36 (3) · 2854-2866

DOI: 10.1109/tcsvt.2025.3613708 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2026-03. Verfasst von Min Li und 5 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 52 Literaturangaben. Gefördert von: Key Research and Development Program of Shandong Province, China, National Natural Science Foundation of China, Taishan Scholars Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The purpose of multimodal industrial anomaly detection is to detect complex geometric shape defects such as subtle surface deformations and irregular contours that are difficult to detect in 2D-based methods. However, current multimodal industrial anomaly detection lacks the effective use of crucial geometric information like surface normal vectors and 3D shape topology, resulting in low detection accuracy. In this paper, we propose a novel Geometric Prior-based Anomaly Detection network (GPAD). Firstly, we propose a point cloud expert model to perform fine-grained geometric feature extraction, employing differential normal vector computation to enhance the geometric details of the extracted features and generate geometric prior. Secondly, we propose a two-stage fusion strategy to efficiently leverage the complementarity of multimodal data as well as the geometric prior inherent in 3D points. We further propose attention fusion and anomaly regions segmentation based on geometric prior, which enhance the model’s ability to perceive geometric defects. Extensive experiments show that our multimodal industrial anomaly detection model outperforms the State-of-the-art (SOTA) methods in detection accuracy on both MVTec-3D AD and Eyecandies datasets.

Förderung

  • Key Research and Development Program of Shandong Province, China
  • National Natural Science Foundation of China
  • Taishan Scholars Program
  • Qilu Youth Innovation Team

Zitieren

APA

Li, M., He, J., Li, G., Li, J., Wan, J., & Han, D. (2026). Multimodal Industrial Anomaly Detection via Geometric Prior. IEEE Transactions on Circuits and Systems for Video Technology, 36(3), 2854-2866. https://doi.org/10.1109/tcsvt.2025.3613708

Vancouver

Li M, He J, Li G, Li J, Wan J, Han D. Multimodal Industrial Anomaly Detection via Geometric Prior. IEEE Transactions on Circuits and Systems for Video Technology. 2026;36(3):2854-2866. doi:10.1109/tcsvt.2025.3613708

BibTeX
@article{Li2026,
  author = {Li, Min and He, Jinghui and Li, Gang and Li, Jiachen and Wan, Jin and Han, Delong},
  title = {Multimodal Industrial Anomaly Detection via Geometric Prior},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2026},
  volume = {36},
  number = {3},
  pages = {2854--2866},
  doi = {10.1109/tcsvt.2025.3613708}
}
Kostenlos starten →