EUVIMEDEUVIMED entdecken
Crossref

All-in-Focus Fourier Ptychographic Microscopy via 3D Implicit Neural Representation

Jingqian Wu, Chutian Wang, Shuo Zhu, Yunfei Tian, Edmund Y. Lam

Advanced Devices & Instrumentation · 2025-01 · 6

DOI: 10.34133/adi.0133 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advanced Devices & Instrumentation, online erschienen am 02.12.2025. Verfasst von Jingqian Wu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 38 Literaturangaben. Gefördert von: Research Grants Council of Hong Kong, Theme-based Research Scheme.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Microscopy has long been essential to biomedical research, enabling detailed analyses of complex samples. Fourier ptychographic microscopy (FPM), a computational imaging technique, provides high-resolution, wide-field images without requiring extensive hardware modifications. However, current FPM algorithms struggle with samples exhibiting depth variations, such as tilted or 3-dimensional (3D) objects. The limited depth of field (DoF) leads to images with only focal-plane areas in sharp focus, while regions outside appear blurred. To address this limitation, we propose an all-in-focus FPM algorithm using physics-informed 3D neural representations to reconstruct sharp, wide-field images of 3D objects under limited DoF. Unlike previous methods, our approach samples the full depth range to create a 3D feature volume that incorporates spatial and depth information. A learnable 3D weight map assigns focus-based weights, emphasizing focused regions while de-emphasizing blurred ones. Additionally, we introduce an unsupervised sharpness loss to optimize the 3D heatmap, forming a new training framework for FPM that enables high-quality reconstruction without direct supervision. Experimental results on real-world microscopy data demonstrate that our approach surpasses existing methods in producing sharp, wide-field reconstructions for samples with depth variation, thus improving performance on downstream vision tasks.

Förderung

  • Research Grants Council of Hong Kong
  • Theme-based Research Scheme

Zitieren

APA

Wu, J., Wang, C., Zhu, S., Tian, Y., & Lam, E. Y. (2025). All-in-Focus Fourier Ptychographic Microscopy via 3D Implicit Neural Representation. Advanced Devices & Instrumentation, 6. https://doi.org/10.34133/adi.0133

Vancouver

Wu J, Wang C, Zhu S, Tian Y, Lam EY. All-in-Focus Fourier Ptychographic Microscopy via 3D Implicit Neural Representation. Advanced Devices & Instrumentation. 2025;6. doi:10.34133/adi.0133

BibTeX
@article{Wu2025,
  author = {Wu, Jingqian and Wang, Chutian and Zhu, Shuo and Tian, Yunfei and Lam, Edmund Y.},
  title = {All-in-Focus Fourier Ptychographic Microscopy via 3D Implicit Neural Representation},
  journal = {Advanced Devices & Instrumentation},
  year = {2025},
  volume = {6},
  doi = {10.34133/adi.0133}
}
Kostenlos starten →