EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep learning for computational imaging: from data-driven to physics-enhanced approaches

Fei Wang, Jürgen W. Czarske, Guohai Situ

Advanced Photonics · 03.09.2025 · 7 (05) · 1-34

DOI: 10.1117/1.ap.7.5.054002 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advanced Photonics, erschienen am 03.09.2025. Verfasst von Fei Wang und 2 weiteren Autor:innen. Die Arbeit wurde bisher 56-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Shanghai Municipal Science and Technology Major Project, National Natural Science Foundation of China, National Key R&D Program of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Computational imaging (CI) leverages the joint optimization of optical system design and reconstruction algorithms, enabling superior performance in terms of dimensionality, resolution, efficiency, and hardware complexity. It has found widespread applications in medical diagnosis and astronomy, among others. Recently, deep learning (DL) has changed the paradigm of CI by harnessing learned priors from data through trained neural network models. However, widely used data-driven DL-based CI methods encounter difficulties related to training data acquisition, computation requirements, generalization, and interpretability. Recent studies have indicated that integrating the physics prior of the CI system into various components of DL pipelines (including training data, network design, and loss functions) holds promise for alleviating these challenges. To provide readers with a better understanding of the current research status and ideas, we present an overview of the state-of-the-art in DL-based CI. We begin by briefly introducing the concepts of CI and DL, followed by a comprehensive review of how DL addresses inverse problems in CI. Particularly, we focus on the emerging physics-enhanced approaches. We highlight the perspectives of future research directions and the transfer to real-world applications.

Förderung

  • Shanghai Municipal Science and Technology Major Project
  • National Natural Science Foundation of China
  • National Key R&D Program of China
  • Program of Shanghai Academic Research Leader
  • Shanghai Sailing Program
  • Reinhart Koselleck project

Zitieren

APA

Wang, F., Czarske, J. W., & Situ, G. (2025). Deep learning for computational imaging: from data-driven to physics-enhanced approaches. Advanced Photonics, 7(05), 1-34. https://doi.org/10.1117/1.ap.7.5.054002

Vancouver

Wang F, Czarske JW, Situ G. Deep learning for computational imaging: from data-driven to physics-enhanced approaches. Advanced Photonics. 2025;7(05):1-34. doi:10.1117/1.ap.7.5.054002

BibTeX
@article{Wang2025,
  author = {Wang, Fei and Czarske, Jürgen W. and Situ, Guohai},
  title = {Deep learning for computational imaging: from data-driven to physics-enhanced approaches},
  journal = {Advanced Photonics},
  year = {2025},
  volume = {7},
  number = {05},
  pages = {1--34},
  doi = {10.1117/1.ap.7.5.054002}
}
Kostenlos starten →