2D_3D Feature Fusion via Cross-Modal Latent Synthesis and Attention Guided Restoration for Industrial Anomaly Detection

TL;DR

This paper introduces MAFR, an unsupervised multi-modal fusion framework combining 2D and 3D data for industrial anomaly detection, achieving state-of-the-art results and robustness in few-shot scenarios.

Contribution

The paper presents a novel fusion architecture that synthesizes a unified latent space from RGB images and point clouds, improving anomaly detection accuracy.

Findings

Achieves state-of-the-art I-AUROC scores of 0.972 and 0.901 on benchmarks.

Demonstrates strong few-shot learning performance.

Ablation studies confirm the importance of fusion architecture and loss functions.

Abstract

Industrial anomaly detection (IAD) increasingly benefits from integrating 2D and 3D data, but robust cross-modal fusion remains challenging. We propose a novel unsupervised framework, Multi-Modal Attention-Driven Fusion Restoration (MAFR), which synthesises a unified latent space from RGB images and point clouds using a shared fusion encoder, followed by attention-guided, modality-specific decoders. Anomalies are localised by measuring reconstruction errors between input features and their restored counterparts. Evaluations on the MVTec 3D-AD and Eyecandies benchmarks demonstrate that MAFR achieves state-of-the-art results, with a mean I-AUROC of 0.972 and 0.901, respectively. The framework also exhibits strong performance in few-shot learning settings, and ablation studies confirm the critical roles of the fusion architecture and composite loss. MAFR offers a principled approach for fusing visual and geometric information, advancing the robustness and accuracy of industrial anomaly detection. Code is available at https://github.com/adabrh/MAFR