EUVIMEDEUVIMED entdecken
Crossref

Improving speckle projection profilometry with deep learning-based digital image correlation

Zizhan Gao, Yanzhao Liu, Jianhui Zhao, Bing Pan

Measurement Science and Technology · 29.10.2026

DOI: 10.1088/1361-6501/aebb50 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Measurement Science and Technology, online erschienen am 29.10.2026. Verfasst von Zizhan Gao und 3 weiteren Autor:innen. Gefördert von: National Natural Science Foundation of China, National Science and Technology Major Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Existing speckle pattern profilometry (SPP) methods for 3D shape measurement generally adopt subset/template-based image matching algorithms for disparity estimation. Despite their attractive merit in single-shot 3D reconstruction, these methods are computationally intensive and often suffer from data loss in regions with sharp gray-level variations or complex surface geometries. To overcome these limitations, an improved SPP using a novel deep-learning based pixelwise image registration framework is introduced. Specifically, a SPP system utilizing a calibrated stereovision setup integrated with a digital projector is established to capture projected speckle patterns. Disparity between the stereo pair that encodes the surface topography is estimated using a state-of-the-art deep learning-based digital image correlation (DL-DIC) framework, called G-RAFT. The estimated disparity is subsequently combined with stereo calibration parameters for triangulation-based 3D reconstruction. By using G-RAFT, the proposed DL-DIC-aided SPP achieves efficient, single-shot, high-accuracy, and dense 3D shape measurement. Experimental results on standard geometries demonstrate that the proposed method achieves reconstruction accuracy comparable to traditional subset/template-based algorithm (Smart-DIC) while providing higher computational efficiency. Experiments on a complex plaster bust further show that this DL-DIC-aided SPP improves reconstruction completeness and robustness in regions where traditional subset-based matching exhibits data loss or mismatches. These results demonstrate that the proposed DL-DIC-aided SPP enables accurate, robust, and dense single-shot 3D reconstruction while preserving the explicit calibration-based geometric reconstruction pipeline.

Förderung

  • National Natural Science Foundation of China
  • National Science and Technology Major Project

Zitieren

APA

Gao, Z., Liu, Y., Zhao, J., & Pan, B. (2026). Improving speckle projection profilometry with deep learning-based digital image correlation. Measurement Science and Technology. https://doi.org/10.1088/1361-6501/aebb50

Vancouver

Gao Z, Liu Y, Zhao J, Pan B. Improving speckle projection profilometry with deep learning-based digital image correlation. Measurement Science and Technology. 2026. doi:10.1088/1361-6501/aebb50

BibTeX
@article{Gao2026,
  author = {Gao, Zizhan and Liu, Yanzhao and Zhao, Jianhui and Pan, Bing},
  title = {Improving speckle projection profilometry with deep learning-based digital image correlation},
  journal = {Measurement Science and Technology},
  year = {2026},
  doi = {10.1088/1361-6501/aebb50}
}
Kostenlos starten →