Image Priors for Single-Shot Coded Diffraction Phase Retrieval
Abstract
Phase retrieval recovers complex-valued objects from intensity-only measurements. In its classical Fourier form, reconstruction suffers from twin-image stagnation. Coded diffraction imaging, which adds a random phase mask before the Fourier transform, has so far required several masks. We show that an image prior makes single-shot coded diffraction imaging possible, with a single random mask followed by a Fourier transform. We validate this claim in simulation and in an optical experiment, in which a spatial light modulator displays the phase object together with the random mask. Our experimental validation covers five test signals and 530 images from the public Brno quantitative phase microscopy dataset of five adherent cell lines. With no image prior or with Fourier-only measurements, reconstruction of complex-valued objects from a single diffraction pattern consistently fails. An out-of-the-box pretrained image denoiser enables accurate reconstruction, in simulation even with fewer measurements than unknowns. Five regularization frameworks built on the same denoiser and one learned weakly convex regularizer all reconstruct the experimental images with peak signal-to-noise ratios within one decibel of each other. A single random phase mask and image priors thus turn coded diffraction imaging into a practical single-shot modality for quantitative phase imaging.
Related
- Dual Branch Transformer with Physical Priors for PSF Acquisition to Enable PSF Guided Image Restoration against Co Phasing Errors in Optical Synthetic Aperture Interferometric Imaging
- ConvexAD: differentiable phase retrieval with geometric regularization for high-strain, low-signal Bragg coherent diffraction imaging
- The Generalized Twin Image: Understanding Regularized Phase Retrieval
- Visualization of Single Spin-chain Propagation using Bragg Coherent Diffraction Imaging
- Single-crystal X-ray diffraction of BC8 carbon near terapascal pressures
BibTeX
@misc{hu2026image,
title = {{Image Priors for Single-Shot Coded Diffraction Phase Retrieval}},
author = {Zhiyuan Hu and YoonSeok Baek and Sylvain Gigan and Michael Unser and Jonathan Dong},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.17064},
eprint = {2610.17064},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.17064},
}
RIS
TY - UNPB
TI - Image Priors for Single-Shot Coded Diffraction Phase Retrieval
AU - Zhiyuan Hu
AU - YoonSeok Baek
AU - Sylvain Gigan
AU - Michael Unser
AU - Jonathan Dong
PY - 2026
DA - 2026/10/12
PB - arXiv
DO - 10.48550/arxiv.2610.17064
UR - https://arxiv.org/abs/2610.17064
AB - Phase retrieval recovers complex-valued objects from intensity-only measurements. In its classical Fourier form, reconstruction suffers from twin-image stagnation. Coded diffraction imaging, which adds a random phase mask before the Fourier transform, has so far required several masks. We show that an image prior makes single-shot coded diffraction imaging possible, with a single random mask followed by a Fourier transform. We validate this claim in simulation and in an optical experiment, in which a spatial light modulator displays the phase object together with the random mask. Our experimental validation covers five test signals and 530 images from the public Brno quantitative phase microscopy dataset of five adherent cell lines. With no image prior or with Fourier-only measurements, reconstruction of complex-valued objects from a single diffraction pattern consistently fails. An out-of-the-box pretrained image denoiser enables accurate reconstruction, in simulation even with fewer measurements than unknowns. Five regularization frameworks built on the same denoiser and one learned weakly convex regularizer all reconstruct the experimental images with peak signal-to-noise ratios within one decibel of each other. A single random phase mask and image priors thus turn coded diffraction imaging into a practical single-shot modality for quantitative phase imaging.
ER -