KIT | KIT-Bibliothek | Impressum | Datenschutz

Analysis of AI-Based Single-View 3D Reconstruction Methods for an Industrial Application

Hartung, Julia ORCID iD icon 1; Dold, Patricia M. 1; Jahn, Andreas; Heizmann, Michael 1
1 Institut für Industrielle Informationstechnik (IIIT), Karlsruher Institut für Technologie (KIT)


Machine learning (ML) is a key technology in smart manufacturing as it provides insights into complex processes without requiring deep domain expertise. This work deals with deep learning algorithms to determine a 3D reconstruction from a single 2D grayscale image. The potential of 3D reconstruction can be used for quality control because the height values contain relevant information that is not visible in 2D data. Instead of 3D scans, estimated depth maps based on a 2D input image can be used with the advantage of a simple setup and a short recording time. Determining a 3D reconstruction from a single input image is a difficult task for which many algorithms and methods have been proposed in the past decades. In this work, three deep learning methods, namely stacked autoencoder (SAE), generative adversarial networks (GANs) and U-Nets are investigated, evaluated and compared for 3D reconstruction from a 2D grayscale image of laser-welded components. In this work, different variants of GANs are tested, with the conclusion that Wasserstein GANs (WGANs) are the most robust approach among them. To the best of our knowledge, the present paper considers for the first time the U-Net, which achieves outstanding results in semantic segmentation, in the context of 3D reconstruction tasks. ... mehr

Verlagsausgabe §
DOI: 10.5445/IR/1000150806
Veröffentlicht am 20.09.2022
DOI: 10.3390/s22176425
Zitationen: 7
Zitationen: 6
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Industrielle Informationstechnik (IIIT)
Publikationstyp Zeitschriftenaufsatz
Publikationsjahr 2022
Sprache Englisch
Identifikator ISSN: 1424-8220
KITopen-ID: 1000150806
Erschienen in Sensors
Verlag MDPI
Band 22
Heft 17
Seiten Art.Nr. 6425
Vorab online veröffentlicht am 25.08.2022
Nachgewiesen in Scopus
Web of Science
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page