EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Cross-Modal Disagreement-Guided Reliability-Aware Scoring for RGB-3D Industrial Anomaly Detection

Jing Xu, Pengfei Xiu, Kun Shi, Lei Xu, Hongliang Wang

Applied Sciences · 01.06.2026 · 16 (11) · 5483

DOI: 10.3390/app16115483 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 01.06.2026. Verfasst von Jing Xu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

RGB–3D industrial anomaly detection seeks to jointly exploit texture and geometric cues for robust defect inspection. However, existing multimodal fusion methods still face two practical limitations: modality-specific anomaly evidence is often weakened after direct fusion, and image-level decisions remain unstable on difficult categories. To address these issues, this study develops a reliability-aware scoring enhancement on top of the released Hybrid Fusion/M3DM memory-bank pipeline. The method constructs a disagreement cue from RGB and point-cloud anomaly responses to enhance suspicious local regions and introduces a dual-branch image-level score calibration that combines a sensitive fusion branch with a robust statistical branch. Evaluated on MVTec 3D-AD under the official released-code full setting, the proposed method achieves 0.800 image-level ROCAUC, 0.980 pixel-level ROCAUC, and 0.926 AU-PRO, compared with 0.779, 0.975, and 0.915 for the corresponding released-code baseline in our environment. Additional evaluation on Eyecandies improves pixel-level ROCAUC and AU-PRO, while showing that image-level calibration remains dataset-sensitive. On a supplementary three-category Real-IAD D3 subset, the mean image-level ROCAUC, pixel-level ROCAUC, and AU-PRO improve from 0.963, 0.979, and 0.921 to 0.980, 0.988, and 0.941, respectively. These results indicate that explicit cross-modal disagreement modeling improves localization consistency, while image-level score calibration provides dataset-dependent gains rather than a uniform cross-dataset guarantee.

Zitieren

APA

Xu, J., Xiu, P., Shi, K., Xu, L., & Wang, H. (2026). Cross-Modal Disagreement-Guided Reliability-Aware Scoring for RGB-3D Industrial Anomaly Detection. Applied Sciences, 16(11), 5483. https://doi.org/10.3390/app16115483

Vancouver

Xu J, Xiu P, Shi K, Xu L, Wang H. Cross-Modal Disagreement-Guided Reliability-Aware Scoring for RGB-3D Industrial Anomaly Detection. Applied Sciences. 2026;16(11):5483. doi:10.3390/app16115483

BibTeX
@article{Xu2026,
  author = {Xu, Jing and Xiu, Pengfei and Shi, Kun and Xu, Lei and Wang, Hongliang},
  title = {Cross-Modal Disagreement-Guided Reliability-Aware Scoring for RGB-3D Industrial Anomaly Detection},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {11},
  pages = {5483},
  doi = {10.3390/app16115483}
}
Kostenlos starten →