Text-Guided Multimodal Unified Industrial Anomaly Detection
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914506223910912 |
|---|---|
| author | Li, Zewen Ye, Shuo Yu, Zitong Xie, Weicheng Shen, Linlin |
| author_facet | Li, Zewen Ye, Shuo Yu, Zitong Xie, Weicheng Shen, Linlin |
| contents | Industrial anomaly detection based on RGB-3D multimodal data has emerged as a mainstream paradigm for intelligent quality inspection. However, existing unsupervised methods suffer from two critical limitations: ambiguous cross-modal alignment caused by the lack of high-level semantic guidance and insufficient geometric modeling for RGB-to-3D feature mapping. To address these issues, we propose a unified multimodal industrial anomaly detection framework guided by text semantics. The framework consists of two core modules: a Geometry-Aware Cross-Modal Mapper to preserve geometric structure during modality conversion, and an Object-Conditioned Textual Feature Adaptor to align multimodal features with semantic priors. Furthermore, we establish a unified learning paradigm for multimodal industrial anomaly detection, which breaks the one-model-one-class constraint and enables accurate anomaly detection across diverse classes using a single model. Extensive experiments on the MVTec 3D-AD and Eyecandies datasets demonstrate that our method achieves state-of-the-art performance in classification and localization under unsupervised settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_22899 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Text-Guided Multimodal Unified Industrial Anomaly Detection Li, Zewen Ye, Shuo Yu, Zitong Xie, Weicheng Shen, Linlin Computer Vision and Pattern Recognition Industrial anomaly detection based on RGB-3D multimodal data has emerged as a mainstream paradigm for intelligent quality inspection. However, existing unsupervised methods suffer from two critical limitations: ambiguous cross-modal alignment caused by the lack of high-level semantic guidance and insufficient geometric modeling for RGB-to-3D feature mapping. To address these issues, we propose a unified multimodal industrial anomaly detection framework guided by text semantics. The framework consists of two core modules: a Geometry-Aware Cross-Modal Mapper to preserve geometric structure during modality conversion, and an Object-Conditioned Textual Feature Adaptor to align multimodal features with semantic priors. Furthermore, we establish a unified learning paradigm for multimodal industrial anomaly detection, which breaks the one-model-one-class constraint and enables accurate anomaly detection across diverse classes using a single model. Extensive experiments on the MVTec 3D-AD and Eyecandies datasets demonstrate that our method achieves state-of-the-art performance in classification and localization under unsupervised settings. |
| title | Text-Guided Multimodal Unified Industrial Anomaly Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.22899 |