Deep Learning-Based 3D Reconstruction for Defect Detection in Shipbuilding Sub-Assemblies

Overshooting defects in shipbuilding subassemblies are essential to ensure the final product’s overall integrity and safety. In this work, we focus on the automatic detection of overshooting defects in simple and T-shaped sub-assemblies by employing reconstruction-based unsupervised learning on 3D p...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Paula Arcano-Bea, Agustín García-Fischer, Pedro-Pablo Gómez-González, Francisco Zayas-Gato, José Luis Calvo-Rolle, Héctor Quintián
Formato:	Artigo
Idioma:	Inglês
Publicado em:	MDPI AG 2026-01-01
coleção:	Sensors
Assuntos:	3D point clouds overshooting defects unsupervised anomaly detection reconstruction-based autoencoders Isolation Forest shipbuilding
Acesso em linha:	https://www.mdpi.com/1424-8220/26/2/660
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!