NeRF-Based defect detection

2025-03-31

AI Summary

To address the challenges of high labor intensity, safety risks, low accuracy, and inadequate coverage of complex curved surfaces and hundred-meter-scale structures in manual inspection for large industrial equipment defect detection, this paper proposes a digital twin–based defect detection method leveraging unmanned aerial vehicle (UAV) multi-view imagery and neural radiance fields (NeRF). It is the first work to introduce NeRF into industrial defect detection, enabling reconstruction of high-fidelity 3D digital twins. Defect localization is achieved automatically and non-invasively by aligning the reference and real-time state models via iterative closest point (ICP) registration, followed by point-cloud deviation analysis. The method overcomes the accuracy and generalization limitations of conventional vision-based approaches in large-scale, highly curved scenarios. Experimental validation demonstrates an average defect localization error of <2.3 mm and enables millimeter-level, full-surface defect identification—significantly enhancing inspection consistency and operational safety.

Technology Category

• Computer Vision: 3D Computer Vision
• Machine Learning: Multi-instance/Multi-view Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

The rapid growth of industrial automation has highlighted the need for precise and efficient defect detection in large-scale machinery. Traditional inspection techniques, involving manual procedures such as scaling tall structures for visual evaluation, are labor-intensive, subjective, and often hazardous. To overcome these challenges, this paper introduces an automated defect detection framework built on Neural Radiance Fields (NeRF) and the concept of digital twins. The system utilizes UAVs to capture images and reconstruct 3D models of machinery, producing both a standard reference model and a current-state model for comparison. Alignment of the models is achieved through the Iterative Closest Point (ICP) algorithm, enabling precise point cloud analysis to detect deviations that signify potential defects. By eliminating manual inspection, this method improves accuracy, enhances operational safety, and offers a scalable solution for defect detection. The proposed approach demonstrates great promise for reliable and efficient industrial applications.

Problem

• Automated defect detection in large-scale machinery using NeRF
• Replacing manual inspection with UAV-captured 3D model comparison
• Enhancing accuracy and safety through digital twin technology

Innovation

• UAV-captured images for 3D model reconstruction
• NeRF and digital twins for defect detection
• ICP algorithm for precise point cloud alignment