EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DCRDF-Net: A Dual-Channel Reverse-Distillation Fusion Network for 3D Industrial Anomaly Detection

Chunshui Wang iD, Jianbo Chen, Heng Zhang iD

Sensors · 08.01.2026 · 26 (2) · 412

DOI: 10.3390/s26020412 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 08.01.2026. Verfasst von Chunshui Wang und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer and Information Science, College of Software, Southwest University, Chongqing 400715, China. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Industrial surface defect detection is essential for ensuring product quality, but real-world production lines often provide only a limited number of defective samples, making supervised training difficult. Multimodal anomaly detection with aligned RGB and depth data is a promising solution, yet existing fusion schemes tend to overlook modality-specific characteristics and cross-modal inconsistencies, so that defects visible in only one modality may be suppressed or diluted. In this work, we propose DCRDF-Net, a dual-channel reverse-distillation fusion network for unsupervised RGB–depth industrial anomaly detection. The framework learns modality-specific normal manifolds from nominal RGB and depth data and detects defects as deviations from these learned manifolds. It consists of three collaborative components: a Perlin-guided pseudo-anomaly generator that injects appearance–geometry-consistent perturbations into both modalities to enrich training signals; a dual-channel reverse-distillation architecture with guided feature refinement that denoises teacher features and constrains RGB and depth students towards clean, defect-free representations; and a cross-modal squeeze–excitation gated fusion module that adaptively combines RGB and depth anomaly evidence based on their reliability and agreement.Extensive experiments on the MVTec 3D-AD dataset show that DCRDF-Net achieves 97.1% image-level I-AUROC and 98.8% pixel-level PRO, surpassing current state-of-the-art multimodal methods on this benchmark.

Schlagwörter

Stichwörter der Autor:innen

3D anomaly detectionmultimodal fusionunsupervised learning

Autor:innen und Institutionen

  • School of Computer and Information Science, College of Software, Southwest University, Chongqing 400715, China.
  • Kawasaki (Chongqing) Robotics Engineering Co., Ltd., Chongqing 400700, China.

ORCID-Profile: Chunshui Wang, Heng Zhang

Zitieren

APA

Wang, C., Chen, J., & Zhang, H. (2026). DCRDF-Net: A Dual-Channel Reverse-Distillation Fusion Network for 3D Industrial Anomaly Detection. Sensors, 26(2), 412. https://doi.org/10.3390/s26020412

Vancouver

Wang C, Chen J, Zhang H. DCRDF-Net: A Dual-Channel Reverse-Distillation Fusion Network for 3D Industrial Anomaly Detection. Sensors. 2026;26(2):412. doi:10.3390/s26020412

BibTeX
@article{Wang2026,
  author = {Wang, Chunshui and Chen, Jianbo and Zhang, Heng},
  title = {DCRDF-Net: A Dual-Channel Reverse-Distillation Fusion Network for 3D Industrial Anomaly Detection},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {2},
  pages = {412},
  doi = {10.3390/s26020412}
}
Kostenlos starten →