Hybrid encoding fringe and simulation-to-real scene approach for accurate depth estimation in fringe projection profilometry
Optics Express · 07.04.2025 · 33 (7) · 14716
DOI: 10.1364/oe.557221 ↗Kurz gefasst
Fachartikel in der Zeitschrift Optics Express, online erschienen am 24.03.2025. Verfasst von Jie Ren und 2 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 40 Literaturangaben. Gefördert von: Science and Technology Department of Sichuan Province.
Abstract (Originalsprache)
Fringe projection profilometry (FPP) is a widely adopted technique for three-dimensional reconstruction, and end-to-end depth estimation based on deep learning has gained considerable attention in recent years. However, this approach often suffers from accuracy limitations and typically requires large amounts of real-world data for training. In this study, we propose what we believe to be a novel hybrid-encoded fringe pattern to replace traditional periodic fringes, thereby enhancing depth estimation accuracy. Additionally, we utilize simulated data for training instead of real-scene data and employ the wrapped phase as network input to bridge the domain gap between simulated and real-world scenarios. We introduce a new network architecture, MSAUNet, designed to extract and fuse multi-scale features effectively. The proposed method is evaluated on the largest real-world dataset to date. Experimental results demonstrate that our method outperforms four existing end-to-end depth estimation techniques. Specifically, for an FPP system with a measurement depth range of 120 mm, we achieve a mean absolute error (MAE) of 0.207 mm for the task of simulation-based training and real-scene inference. The source code and dataset will be made publicly available.
Förderung
- Science and Technology Department of Sichuan Province
Zitieren
APA
Ren, J., Tan, C., & Song, W. (2025). Hybrid encoding fringe and simulation-to-real scene approach for accurate depth estimation in fringe projection profilometry. Optics Express, 33(7), 14716. https://doi.org/10.1364/oe.557221
Vancouver
Ren J, Tan C, Song W. Hybrid encoding fringe and simulation-to-real scene approach for accurate depth estimation in fringe projection profilometry. Optics Express. 2025;33(7):14716. doi:10.1364/oe.557221
BibTeX
@article{Ren2025,
author = {Ren, Jie and Tan, Chunqian and Song, Wanzhong},
title = {Hybrid encoding fringe and simulation-to-real scene approach for accurate depth estimation in fringe projection profilometry},
journal = {Optics Express},
year = {2025},
volume = {33},
number = {7},
pages = {14716},
doi = {10.1364/oe.557221}
}
EUVIMED