EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

PIV-FlowDiffuser: Transfer-Learning-Based Denoising Diffusion Models for Particle Image Velocimetry

Qianyu Zhu iD, Junjie Wang iD, Jeremiah Hu iD, Jia Ai iD, Yong Lee iD

Sensors · 02.10.2025 · 25 (19) · 6077

DOI: 10.3390/s25196077 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 02.10.2025. Verfasst von Qianyu Zhu und 4 weiteren Autor:innen. Beteiligte Einrichtung: Hubei Provincial Engineering Research Center of Robotics & Intelligent Manufacturing, School of Mechanical and Electronic Engineering, Wuhan Universi…. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Hubei Province, Hubei Provincial Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep learning algorithms have significantly reduced the computational time and improved the spatial resolution of particle image velocimetry (PIV). However, the models trained on synthetic datasets might have degraded performances on practical particle images due to domain gaps. As a result, special residual patterns are often observed for the vector fields of deep learning-based estimators. To reduce the special noise step by step, we employ a denoising diffusion model (FlowDiffuser) for PIV analysis. And a data-hungry iterative denoising diffusion model is trained via a transfer learning strategy, resulting in our PIV-FlowDiffuser method. Specifically, we carry out the following: (1) pre-training a FlowDiffuser model with multiple optical flow datasets of the computer vision community, such as Sintel and KITTI; (2) fine-tuning the pre-trained model on synthetic PIV datasets. Note that the PIV images are upsampled by a factor of two to resolve small-scale turbulent flow structures. The visualized results indicate that our PIV-FlowDiffuser effectively suppresses the noise patterns. Therefore, the denoising diffusion model reduces the average endpoint error (AEE) by 59.4% over the RAFT256-PIV baseline on the classic Cai’s dataset. In addition, PIV-FlowDiffuser exhibits enhanced generalization performance on unseen particle images due to transfer learning. Overall, this study highlights transfer-learning-based denoising diffusion models for PIV.

Schlagwörter

Stichwörter der Autor:innen

denoising diffusion modelgeneralization performanceoptical flow estimationparticle image velocimetrytransfer learning

Autor:innen und Institutionen

  • Hubei Provincial Engineering Research Center of Robotics & Intelligent Manufacturing, School of Mechanical and Electronic Engineering, Wuhan University of Technology (WHUT), Wuhan 430070, China.

ORCID-Profile: Qianyu Zhu, Junjie Wang, Jeremiah Hu, Jia Ai, Yong Lee

Förderung

  • Natural Science Foundation of Hubei Province
  • Hubei Provincial Natural Science Foundation of China

Zitieren

APA

Zhu, Q., Wang, J., Hu, J., Ai, J., & Lee, Y. (2025). PIV-FlowDiffuser: Transfer-Learning-Based Denoising Diffusion Models for Particle Image Velocimetry. Sensors, 25(19), 6077. https://doi.org/10.3390/s25196077

Vancouver

Zhu Q, Wang J, Hu J, Ai J, Lee Y. PIV-FlowDiffuser: Transfer-Learning-Based Denoising Diffusion Models for Particle Image Velocimetry. Sensors. 2025;25(19):6077. doi:10.3390/s25196077

BibTeX
@article{Zhu2025,
  author = {Zhu, Qianyu and Wang, Junjie and Hu, Jeremiah and Ai, Jia and Lee, Yong},
  title = {PIV-FlowDiffuser: Transfer-Learning-Based Denoising Diffusion Models for Particle Image Velocimetry},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {19},
  pages = {6077},
  doi = {10.3390/s25196077}
}
Kostenlos starten →