EUVIMEDEUVIMED entdecken
Crossref

U-ResNet-ESPI: a physics-informed deep learning framework for robust phase unwrapping in electronic speckle pattern interferometry

Kejia Li, ZeYu Li, Jinqu Feng, Zixin Zhao, Wenrui Liu, Hong Zhao, Lu Zhang, Chen Fan, Gaopeng Zhang, Mohan Gao

Optics Express · 04.05.2026 · 34 (9) · 17304

DOI: 10.1364/oe.591358 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Optics Express, online erschienen am 01.05.2026. Verfasst von Kejia Li und 9 weiteren Autor:innen. Die Arbeit nennt 34 Literaturangaben. Gefördert von: National Natural Science Foundation of China, China Postdoctoral Science Foundation, Scientific Research Program Funded by Shaanxi Provincial Education Department.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Electronic speckle pattern interferometry (ESPI) is a non-contact, full-field measurement technique whose precision hinges on robust phase unwrapping. However, high-speckle-noise often compromises phase continuity in conventional algorithms. To address this, we propose U-ResNet-ESPI, a noise-robust deep learning architecture for accurate phase recovery. It combines physics-driven data synthesis, a physics-aware multi-view preprocessing, and an optimized U-Net with a topology-aware hybrid loss to reduce the synthetic-to-real domain gap. improve robustness to varying levels of speckle noise, and preserve phase continuity. Experimental results show that the proposed method achieves accurate phase recovery even under severe noise conditions with an error level of only 0.01 rad, significantly outperforming traditional algorithms. This approach improves the reliability of ESPI measurements and can be extended to other coherent imaging modalities such as digital holography and stereography.

Förderung

  • National Natural Science Foundation of China
  • China Postdoctoral Science Foundation
  • Scientific Research Program Funded by Shaanxi Provincial Education Department
  • Shaanxi Provincial Science and Technology Plan Project - Key Research and Development Plan
  • Youth Innovation Promotion Association, Chinese Academy of Sciences

Zitieren

APA

Li, K., Li, Z., Feng, J., Zhao, Z., Liu, W., Zhao, H., Zhang, L., Fan, C., Zhang, G., & Gao, M. (2026). U-ResNet-ESPI: a physics-informed deep learning framework for robust phase unwrapping in electronic speckle pattern interferometry. Optics Express, 34(9), 17304. https://doi.org/10.1364/oe.591358

Vancouver

Li K, Li Z, Feng J, Zhao Z, Liu W, Zhao H, et al. U-ResNet-ESPI: a physics-informed deep learning framework for robust phase unwrapping in electronic speckle pattern interferometry. Optics Express. 2026;34(9):17304. doi:10.1364/oe.591358

BibTeX
@article{Li2026,
  author = {Li, Kejia and Li, ZeYu and Feng, Jinqu and Zhao, Zixin and Liu, Wenrui and Zhao, Hong and Zhang, Lu and Fan, Chen and Zhang, Gaopeng and Gao, Mohan},
  title = {U-ResNet-ESPI: a physics-informed deep learning framework for robust phase unwrapping in electronic speckle pattern interferometry},
  journal = {Optics Express},
  year = {2026},
  volume = {34},
  number = {9},
  pages = {17304},
  doi = {10.1364/oe.591358}
}
Kostenlos starten →