Text-Guided Multimodal Unified Industrial Anomaly Detection

TL;DR

This paper introduces a text-guided multimodal framework for industrial anomaly detection that improves cross-modal alignment and geometric modeling, enabling accurate unsupervised detection across diverse classes.

Contribution

It proposes a unified multimodal anomaly detection framework with novel modules for semantic guidance and geometric preservation, breaking the one-model-one-class constraint.

Findings

Achieves state-of-the-art results on MVTec 3D-AD and Eyecandies datasets.

Effectively aligns multimodal features with semantic priors.

Handles diverse classes with a single model.

Abstract

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.