EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

HFMM-Net: A Hybrid Fusion Mamba Network for Efficient Multimodal Industrial Defect Detection

Guo Zhao, Liang Tan, Musong He, Qi Wu

Information · 23.11.2025 · 16 (12) · 1018

DOI: 10.3390/info16121018 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Information, online erschienen am 23.11.2025. Verfasst von Guo Zhao und 3 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the increasing demand for higher precision and real-time performance in industrial surface defect detection, multimodal detection methods integrating RGB images and 3D point clouds have drawn considerable attention. However, current mainstream methods typically employ computationally expensive Transformer-based models for capturing global features, resulting in significant inference delays that hinder their practical deployment for online inspection tasks. Furthermore, existing approaches exhibit limited capability in deep cross-modal interactions, negatively impacting defect detection and segmentation accuracy. In this paper, we propose a novel multimodal anomaly detection framework based on a bidirectional Mamba network to enhance cross-modal feature interaction and fusion. Specifically, we introduce an anomaly-aware parallel feature extraction network, leveraging a hybrid scanning state space model (SSM) to efficiently capture global and long-range dependencies with linear computational complexity. Additionally, we develop a cross-enhanced feature fusion module to facilitate dynamic interaction and adaptive fusion of multimodal features at multiple scales. Extensive experiments conducted on two publicly available benchmark datasets, MVTec 3D-AD and Eyecandies, demonstrate that the proposed method consistently outperforms existing approaches in both defect detection and segmentation tasks.

Zitieren

APA

Zhao, G., Tan, L., He, M., & Wu, Q. (2025). HFMM-Net: A Hybrid Fusion Mamba Network for Efficient Multimodal Industrial Defect Detection. Information, 16(12), 1018. https://doi.org/10.3390/info16121018

Vancouver

Zhao G, Tan L, He M, Wu Q. HFMM-Net: A Hybrid Fusion Mamba Network for Efficient Multimodal Industrial Defect Detection. Information. 2025;16(12):1018. doi:10.3390/info16121018

BibTeX
@article{Zhao2025,
  author = {Zhao, Guo and Tan, Liang and He, Musong and Wu, Qi},
  title = {HFMM-Net: A Hybrid Fusion Mamba Network for Efficient Multimodal Industrial Defect Detection},
  journal = {Information},
  year = {2025},
  volume = {16},
  number = {12},
  pages = {1018},
  doi = {10.3390/info16121018}
}
Kostenlos starten →