# IAENet: An Importance-Aware Ensemble Model for 3D Point Cloud-Based Anomaly Detection

## TL;DR

This paper introduces IAENet, a novel ensemble framework combining 2D pretrained and 3D models for improved surface anomaly detection in industrial manufacturing, addressing the lack of powerful 3D backbones.

## Contribution

We propose a dynamic importance-aware fusion module and specialized loss functions to effectively combine 2D and 3D experts, achieving state-of-the-art results in 3D anomaly detection.

## Key findings

- Achieves state-of-the-art performance on MVTec 3D-AD dataset.
- Significantly reduces false positive rates.
- Demonstrates practical industrial deployment potential.

## Abstract

Surface anomaly detection is pivotal for ensuring product quality in industrial manufacturing. While 2D image-based methods have achieved remarkable success, 3D point cloud-based detection remains underexplored despite its richer geometric cues. We argue that the key bottleneck is the absence of powerful pretrained foundation backbones in 3D comparable to those in 2D. To bridge this gap, we propose Importance-Aware Ensemble Network (IAENet), an ensemble framework that synergizes 2D pretrained expert with 3D expert models. However, naively fusing predictions from disparate sources is non-trivial: existing strategies can be affected by a poorly performing modality and thus degrade overall accuracy. To address this challenge, We introduce an novel Importance-Aware Fusion (IAF) module that dynamically assesses the contribution of each source and reweights their anomaly scores. Furthermore, we devise critical loss functions that explicitly guide the optimization of IAF, enabling it to combine the collective knowledge of the source experts but also preserve their unique strengths, thereby enhancing the overall performance of anomaly detection. Extensive experiments on MVTec 3D-AD demonstrate that our IAENet achieves a new state-of-the-art with a markedly lower false positive rate, underscoring its practical value for industrial deployment.