Skip to main navigation Skip to search Skip to main content

Physics-informed neural fields enable blind aberration correction for partially coherent quantitative phase imaging

  • Shun Zhou (Co-first Author)
  • , Xingyu Huang (Co-first Author)
  • , Linpeng Lu
  • , Habib Ullah
  • , Kaiyu Du
  • , Maciej Trusiak
  • , Malgorzata Kujawinska
  • , Yuzhen Zhang
  • , Yao Fan*
  • , Qian Chen*
  • , Qinrong Zhang*
  • , Chao Zuo*
  • *Corresponding author for this work

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

4 Downloads (CityUHK Scholars)

Abstract

Partially coherent quantitative phase imaging (QPI) underpins label-free microscopy and optical metrology, providing stable, speckle-suppressed phase measurement with a brightfield-compatible platform and resolution beyond the coherent diffraction limit. However, its image formation is governed by a high-dimensional bilinear forward model, making linearized analytic inversions such as differential phase contrast (DPC) prone to model mismatch and biased reconstruction under large phase excursions, strong absorption, and optical aberrations. Here, we introduce USDPC, a universal neural-field solver for DPC, that performs physics-constrained, unsupervised inver-sion of the strict nonlinear intensity-to-phase relationship under partially coherent illumination. USDPC represents the specimen's complex transmittance and pupil aberrations as implicit neural fields and jointly optimizes them via a differentiable bilinear forward operator, enabling accurate phase recovery beyond the weak-object regime while self-calibrating unknown aberrations without additional calibration data or acquisition overhead. Comprehensive simulations and experimental validations on microlens arrays, resolution targets, stained histological sections, and live HeLa cells demonstrate the effectiveness and universality of USDPC, and highlight physics-informed neural fields as a versatile computational framework for solving challenging nonlinear inverse problems in computational imaging and beyond. ©The Author(s) 2026.
Original languageEnglish
Article number260019
Number of pages14
JournalOpto-Electronic Science
Volume5
Issue number8
Online published26 Aug 2026
DOIs
Publication statusPublished - Aug 2026

Funding

This work was supported by the National Key Research and Development Program of China (Nos. 2024YFE0101300, 2022YFA1205002, 2024YFF0505603, 2024YFF0505600); National Natural Science Foundation of China (Nos. 62227818, 62361136588, 62305162, U21B2033)

Research Keywords

  • aberration correction
  • differential phase contrast microscopy
  • neural fields
  • nonlinear inverse problem
  • phase retrieval

Publisher's Copyright Statement

  • This full text is made available under CC-BY 4.0. https://creativecommons.org/licenses/by/4.0/

Fingerprint

Dive into the research topics of 'Physics-informed neural fields enable blind aberration correction for partially coherent quantitative phase imaging'. Together they form a unique fingerprint.

Cite this