prNet: Data-Driven Phase Retrieval via Stochastic Refinement
Listen
Radio episode about this paper
Transcript
Introduction to the show: ident: Electrical Engineering. The day in electrical engineering: signals, systems and the hardware that carries them.
Rosa: I'm Rosa.
Dev: And I'm Dev, here with Taro.
Rosa: We're looking at the paper: "prNet: Data-Driven Phase Retrieval via Stochastic Refinement".
Dev: Here's the gist of the paper. Phase retrieval is an ill-posed inverse problem in which classical and deep learning–based methods struggle to jointly achieve measurement fidelity and perceptual realism.
Rosa: We propose a novel framework for phase retrieval that leverages Langevin dynamics to enable efficient posterior sampling, yielding reconstructions that explicitly balance distortion and perceptual quality.
Dev: Unlike conventional approaches that prioritize pixel-wise accuracy, our methods navigate the perception-distortion tradeoff through a principled combination of stochastic sampling, learned denoising, and model-based updates.
Rosa: The Problem Context Phase retrieval involves reconstructing an unknown signal from noisy intensity measurements where the problem is highly non-linear and illposed.
Paper summary: Rosa: So to wrap up, the paper prNet: Data-Driven Phase Retrieval via Stochastic Refinement proposes a new way to handle phase retrieval by using Langevin dynamics for sampling from the posterior distribution.
Dev: The authors claim this framework yields reconstructions that explicitly balance distortion and perceptual quality, moving beyond methods that just try to be pixel-wise accurate.
Taro: It seems like the core contribution is structuring the problem into three variants, prNet-Small, prNet-Large, and prNet-Large-Adv.
Rosa: PrNet-Small uses Langevin dynamics with learned noise and denoising processes along with model driven HIO updates as its foundation.
Dev: PrNet-Large uses parallel sampling of diverse reconstructions to approximate the mean squared error solution through ensemble averaging to improve distortion metrics.
Taro: And prNet-Large-Adv builds on that by adding an adversarially trained aggregation network to specifically enhance perceptual quality while trying to maintain fidelity.
Rosa: The big picture is that this approach uses a principled combination of stochastic sampling and learned denoiser models within the Langevin dynamics framework to tackle the ill-posed nature of phase retrieval.
Dev: It suggests that combining these model-based updates with data-driven priors in a stochastic refinement framework could lead to more reliable solvers for nonlinear inverse problems.
Taro: For someone just listening, this means there's a new direction for how we tackle these hard inverse problems, focusing on the trade off between what the math tells you and what looks realistic.
Conclusion: Rosa: So, to wrap up this discussion about prNet: Data-Driven Phase Retrieval via Stochastic Refinement, we're looking at what these authors actually achieved here and what that means for us out here in the real world.
Dev: The title itself is a mouthful, but essentially, they’ve put together a framework that uses Langevin dynamics to sample from the probability distribution of the signal.
Taro: That’s right, it’s about using these stochastic updates to find a better reconstruction than what you get from just one shot of data.
Rosa: They tackle that problem by building three versions: prNet-Small, prNet-Large, and then the prNet-Large-Adv version which adds a little extra sharpening.
Dev: The core idea is balancing how accurate the image looks—the fidelity—with how realistic it actually seems to an observer.
Taro: It’s about navigating that distortion versus perceptual quality tradeoff, not just chasing pixel perfect noise reduction.
Rosa: They show that this combination of sampling and learned denoisers works really well across different benchmarks for phase retrieval.
Dev: The results are consistent: they beat the other methods on both traditional error metrics and those measures of how realistic the image looks to a human eye, like the SSIM score.
Taro: What’s interesting is that it doesn't introduce those weird artifacts you sometimes see when you push these models too far.
Rosa: They kept the runtime pretty reasonable compared to other complex setups, which is important for practical application on real hardware.
Dev: So, the authors suggest that coupling model-based updates with these stochastic refinement methods is a promising path for solving hard nonlinear problems in imaging.
Taro: It opens up a way for us to build more robust solvers when the world throws some weird data at us.
Rosa: And it sets up a question: can we take this framework and test it outside of the clean lab environment?
Middle East Technical University · Technical University of Denmark
eess.IV, cs.CV
Submitted: 2025-07-13
Updated: 2026-11-05
Comments: Accepted at IEEE Transactions on Computational Imaging (2026)
Journal ref: IEEE Transactions on Computational Imaging, vol. 12, pp. 1376-1391, 2026
Code: https://github.com/METU-SPACE-Lab/prNet-forPhase-Retrieval
License: http://creativecommons.org/licenses/by/4.0/
Importance score: 92/100
The gist: Phase retrieval is an ill-posed inverse problem in which classical and deep learning–based methods struggle to jointly achieve measurement fidelity and perceptual realism.
Key concepts
- Langevin Dynamics
- This is a stochastic sampling method used to explore the complex probability distribution of possible solutions for phase retrieval. By incorporating learned noise and a denoiser model, it allows the algorithm to efficiently sample from the posterior distribution p(x|y), leading to more robust reconstructions than traditional methods.
- Perception-Distortion Tradeoff
- This is the central challenge in phase retrieval: finding a solution that is both accurate (high fidelity) and visually realistic (perceptual quality). The framework addresses this by strategically combining stochastic sampling, learned denoising, and model updates to find a principled balance between these two competing goals.
- Hybrid Input-Output (HIO) Algorithm
- The HIO algorithm is used within the Langevin dynamics update step to improve convergence properties. It allows the process to start from a good initial guess derived from classical solvers, speeding up the overall reconstruction process and enhancing stability.
Terminology
Summary
Phase retrieval is an ill-posed inverse problem in which classical and deep learning–based methods struggle to jointly achieve measurement fidelity and perceptual realism. p. 0 1
prNet: Data-Driven Phase Retrieval
via Stochastic Refinement
Mehmet Onurcan Kaya and Figen S. Oktem , Member, IEEE
Abstract—Phase retrieval is an ill-posed inverse problem in
which classical and deep learning–based methods struggle to
jointly achieve measurement fidelity and perceptual realism. Oktem , Member, IEEE
Abstract—Phase retrieval is an ill-posed inverse problem in
which classical and deep learning–based methods struggle to
jointly achieve measurement fidelity and perceptual realism. We propose a novel framework for phase retrieval that leverages Langevin dynamics to enable efficient posterior sampling,
yielding reconstructions that explicitly balance distortion and
perceptual quality. We propose a novel framework for phase retrieval that leverages Langevin dynamics to enable efficient posterior sampling,
yielding reconstructions that explicitly balance distortion and
perceptual quality. Unlike conventional approaches that prioritize pixel-wise accuracy, our methods navigate the perceptiondistortion tradeoff through a principled combination of stochastic
sampling, learned denoising, and model-based updates.Where the paper says it
Where the paper says it
Where the paper says it
The Problem Context
Phase retrieval involves reconstructing an unknown signal from noisy intensity measurements where the problem is highly non-linear and illposed. Classical approaches like the Error Reduction (ER) algorithm are sensitive to initialization and often stagnate at suboptimal solutions. p. 0 Among the earliest of these is the Error Reduction (ER)
algorithm [3], which strictly applies hard projections at each
step. While simple and computationally efficient, ER is highly
sensitive to initialization and often stagnates at suboptimal solutions. Such estimators tend to produce
overly smooth outputs with reduced perceptual fidelity due to
the perception-distortion tradeoff [14]. To address these limitations, deep generative models, particularly score/diffusion-based approaches, have gained traction
for their ability to sample from the posterior distribution for
many inverse problems [15].Where the paper says it
Where the paper says it
Framework Components
The proposed framework consists of three progressively more advanced methods: (1) prNet-Small, which integrates Langevin dynamics with learned noise and denoising processes and model-driven HIO updates. (2) prNet-Large, which exploits parallel sampling of diverse reconstructions to approximate the MMSE solution via ensemble averaging. p. 1 We propose a novel diffusion-based framework for phase
retrieval that bridges model-driven and data-driven approaches. Our framework consists of three progressively more advanced methods: (1) prNet-Small, a theoretically grounded and
lightweight pipeline that integrates Langevin dynamics with
learned noise and denoising processes and model-driven HIO
updates; (2) prNet-Large, which exploits parallel sampling of
diverse reconstructions to approximate the MMSE solution
via ensemble averaging, significantly improving distortion
metrics; and (3) prNet-Large-Adv, extending prNet-Large with
an adversarially-trained aggregation network to enhance perceptual quality while preserving fidelity. We propose a novel diffusion-based framework for phase
retrieval that bridges model-driven and data-driven approaches. Our framework consists of three progressively more advanced methods: (1) prNet-Small, a theoretically grounded and
lightweight pipeline that integrates Langevin dynamics with
learned noise and denoising processes and model-driven HIO
updates; (2) prNet-Large, which exploits parallel sampling of
diverse reconstructions to approximate the MMSE solution
via ensemble averaging, significantly improving distortion
metrics; and (3) prNet-Large-Adv, extending prNet-Large with
an adversarially-trained aggregation network to enhance perceptual quality while preserving fidelity.Where the paper says it
Where the paper says it
Stochastic Refinement Mechanism
The core of the method is based on Langevin dynamics to sample from the posterior distribution p(xy) using both the score function and injected Gaussian noise. This involves an update step derived from Bayes’ rule for the posterior score function, which incorporates a learned denoiser model Dθ to approximate the unconditional score function. p. 4 Hence our approach
is based on the following update step [15]:
xt+1 ← xt + γ∇x log p (xt|y) + p
2γvt, 1 ≤ t ≤ T, (6)
where γ denotes the step size, vt ∼ N (0, I) is standard
Gaussian noise, and T is the total number of iterations. Using
Bayes’ rule for the score function of the posterior yields:
xt+1 ← xt+γ∇x log p (xt)+γ∇x log p (y|xt)+p
2γvt (7)
We use a learned denoiser model Dθ with parameters θ
to approximate the unconditional score function, assuming
degradation with xt ≜ x + v where v ∼ N (0, σ2
t
I) [47]:
∇x log p (xt) = Dθ (xt, t) − xt
σ
2
t
. 6
To address this, we can substitute this step with the Hybrid Input-Output (HIO) algorithm, which demonstrates better
convergence properties in practice. This important improvement [12], [30] is often overlooked in prior diffusion-based PR
methods such as [18], which typically follow simpler update
rules with limited convergence behavior.Where the paper says it
Where the paper says it
Performance Enhancements
The prNet-Large pipeline enhances reconstruction quality through multiple parallel reconstructions, where each estimate is passed through a denoiser to yield refined outputs. The prNet-Large-Adversarial pipeline further incorporates a second denoiser with a Wasserstein loss to enhance perceptual quality alongside distortion metrics. p. 7 To train the final denoiser Dϕ in the prNet-LargeAdversarial pipeline, we incorporate an additional improved
Wasserstein GAN loss with gradient penalty [65] term into
the training objective. This term addresses perceptual quality
alongside distortion metrics, helping to balance the perceptiondistortion tradeoff. By incorporating all transformations from the D4 dihedral
group, this advanced TTA technique maximizes the use of
symmetry properties and available data, significantly enhancing the robustness and quality of image reconstructions. This
approach is particularly effective in image reconstruction tasks,
where the enriched data from augmentation helps mitigate
overfitting and improves generalization performance.Where the paper says it
Where the paper says it
Experimental Validation
Extensive experiments demonstrate that our methods achieve state-of-the-art performance across multiple benchmarks, both in terms of fidelity and perceptual quality. The developed approach consistently surpasses other methods in both PSNR and SSIM metrics across all noise levels, while only necessitating a marginal increase in runtime compared to the initialization stage. p. 8 Table I presents the average reconstruction performance
of the algorithms for 236 test images over 5 Monte Carlo
runs under varying levels of Poisson noise (α = 2, 3, 4). The
developed methods consistently surpass other methods in both
PSNR and SSIM metrics across all noise levels, while only
necessitating a marginal increase in runtime compared to the
initialization stage. With our methods, HIO artifacts can be successfully removed while preserving the image characteristics. Our approach generally does not introduce artifacts and errors like the
other methods.Where the paper says it
Where the paper says it
Conclusion
Our results suggest that the combination of denoisers with model-based methods in the Langevin dynamics framework shows promise for developing reliable stochastic solvers for nonlinear inverse problems. The paper introduces a novel approach to phase retrieval using Langevin dynamics for posterior sampling. p. 0 Oktem , Member, IEEE
Abstract—Phase retrieval is an ill-posed inverse problem in
which classical and deep learning–based methods struggle to
jointly achieve measurement fidelity and perceptual realism. We propose a novel framework for phase retrieval that leverages Langevin dynamics to enable efficient posterior sampling,
yielding reconstructions that explicitly balance distortion and
perceptual quality. Table I presents the average reconstruction performance
of the algorithms for 236 test images over 5 Monte Carlo
runs under varying levels of Poisson noise (α = 2, 3, 4). The
developed methods consistently surpass other methods in both
PSNR and SSIM metrics across all noise levels, while only
necessitating a marginal increase in runtime compared to the
initialization stage. Moreover,
our framework demonstrates promise for developing reliable
stochastic nonlinear inverse problem solvers, which could have
broader implications beyond PR. Some preliminary results of
this research were presented in [19].Where the paper says it
Where the paper says it
Where the paper says it
Acknowledgments
This study was funded in part by Scientific and Technological Research Council of Turkey (TUBITAK) under the Grant Number 120E505.
References
[1] J. Dong, L. Valzania, A. Maillard, T.-a. Pham, S. Gigan, and M. Unser, “Phase retrieval: From computational imaging to machine learning,” IEEE Signal Processing Magazine, vol. p. 0 Index Terms—Phase retrieval, diffusion models, deep learning,
inverse problems, computational imaging. INTRODUCTION
P
HASE retrieval (PR) is a fundamental inverse problem
in many scientific and engineering disciplines, where the
goal is to reconstruct a signal using only intensity measurements such as Fourier intensities.Where the paper says it
[2] C. Metzler, P. Schniter, A. Veeraraghavan, and R. Baraniuk, “PrDeep: Robust phase retrieval with a flexible deep network,” in ICML, 2018 ref:2507.096084[2]
[3] J. R. Fienup, “Reconstruction of an object from the modulus of its fourier transform,” Optics Letters, vol. p. 8 Our experiments focus on the classical Fourier phase retrieval problem,
which involves recovering an image from the magnitude of
its Fourier transform. We assess generalization capability and
computational efficiency, and compare reconstruction quality
against both classical and state-of-the-art phase retrieval algorithms.Where the paper says it
[4] J. R. Fienup, “Phase retrieval algorithms: A comparison,” Applied Optics, vol. p. 8 For
comparison, we present the results for prDeep [2], HIO [3],
DIR [29], and MBwDDP [12], [30]. Table I presents the average reconstruction performance
of the algorithms for 236 test images over 5 Monte Carlo
runs under varying levels of Poisson noise (α = 2, 3, 4).Where the paper says it
[5] S. Marchesini, “Invited article: A unified evaluation of iterative projection algorithms for phase retrieval,” Review of scientific instruments, vol. p. 1 Iterative Projection Techniques for Phase Retrieval
Iterative projection techniques have become fundamental
tools for phase retrieval. One of the earliest and most wellknown algorithms is the classical Gerchberg-Saxton (GS)
algorithm [20], which iteratively applies magnitude constraints
in both the spatial and measurement domains to reconstruct
an unknown signal.Where the paper says it
[6] I. Waldspurger, A. d’Aspremont, and S. Mallat, “Phase recovery, maxcut and complex semidefinite programming,” Mathematical Programming, vol. p. 0 Nevertheless, both ER and HIO remain vulnerable to noise,
artifacts, and local minima, particularly in high-dimensional or
low-SNR regimes [5]. To mitigate these issues, more advanced
techniques have been developed, including methods based on
semidefinite programming and sparse regularization.Where the paper says it
[7] K. Jaganathan, S. Oymak, and B. Hassibi, “Sparse phase retrieval: Convex algorithms and limitations,” in ISIT, 2013 ref:2507.096084[7]
[8] S. Lopez-Tapia, R. Molina, and A. Katsaggelos, “Deep learning ap- proaches to inverse problems in imaging: Past, present and future,” Digital Signal Processing, vol. p. 0 Index Terms—Phase retrieval, diffusion models, deep learning,
inverse problems, computational imaging. INTRODUCTION
P
HASE retrieval (PR) is a fundamental inverse problem
in many scientific and engineering disciplines, where the
goal is to reconstruct a signal using only intensity measurements such as Fourier intensities.Where the paper says it
[9] K. Wang et al., “On the use of deep learning for phase recovery,” Light: Science & Applications, vol. p. 2 This hybrid approach, which combines neural networks
with analytical methods, has demonstrably succeeded in various real-valued 2D reconstruction problems, including deconvolution, super-resolution, tomography, and phase retrieval
[10], [13], [25]. A key advantage of learning-based direct
inversion methods lies in their low computational complexity
due to their feed-forward (non-iterative) nature, making them
suitable for real-time imaging applications.Where the paper says it
[10] K. H. Jin, M. T. McCann, E. Froustey, and M. A. Unser, “Deep convolutional neural network for inverse problems in imaging,” IEEE Transactions on Image Processing, vol. p. 0 In recent years, deep learning has emerged as a powerful
tool for solving various inverse problems in imaging, including
phase retrieval [8], [9]. Data-driven approaches based on
deep neural networks (DNNs) have demonstrated remarkable
success in directly reconstructing images from measurements
or refining initial estimates from classical methods [10].Where the paper says it
[11] Y. Romano, M. Elad, and P. Milanfar, “The little engine that could: Regularization by denoising (red),” SIAM Journal on Imaging Sciences, vol. p. 2 A key advantage of learning-based direct
inversion methods lies in their low computational complexity
due to their feed-forward (non-iterative) nature, making them
suitable for real-time imaging applications. In contrast to learning-based direct inversion, plug-andplay regularization, and unrolled learning methods embrace
iterative strategies.Where the paper says it
[12] C¸. Is¸ıl and F. p. 2 As theoretically shown in [14] and
empirically observed in [40], these estimates may deviate
significantly from the natural image manifold, leading to
reconstructions with overly smooth features. Interestingly, the
work by Is¸ıl et al. As theoretically shown in [14] and
empirically observed in [40], these estimates may deviate
significantly from the natural image manifold, leading to
reconstructions with overly smooth features. Interestingly, the
work by Is¸ıl et al. Alternatively, model-based optimization schemes have been
augmented with deep priors learned from data using the
plug-and-play framework [11], [12]. However, existing deep
learning solutions for phase retrieval often suffer from limited
performance due to domain shift, which occurs when the training data and real-world test data follow different distributions,
leading to degraded accuracy [13].Where the paper says it
Where the paper says it
Where the paper says it
[13] W. Zhang, Y. Wan, Z. Zhuang, and J. Sun, “What’s wrong with end-to-end learning for phase retrieval? p. 1 While achieving state-of-the-art performance
for simpler inverse problems such as denoising [24], these
methods face challenges with complex observation models,
significant discrepancies between observations and the target
image, or limited training data availability. Such end-to-end
direct inversion schemes also exist for the phase retrievalWhere the paper says it
[14] Y. Blau and T. Michaeli, “The perception-distortion tradeoff,” in CVPR, 2018 ref:2507.096084[14]
[15] B. Kawar, G. Vaksman, and M. Elad, “Snips: Solving noisy inverse problems stochastically,” in NeurIPS, 2021 ref:2507.096084[15]
[16] C. Luo, “Understanding diffusion models: A unified perspective,” ArXiv, 2022 ref:2507.096084[16]
[17] M. O. Kaya and F. p. 0 1
prNet: Data-Driven Phase Retrieval
via Stochastic Refinement
Mehmet Onurcan Kaya and Figen S. Oktem , Member, IEEE
Abstract—Phase retrieval is an ill-posed inverse problem in
which classical and deep learning–based methods struggle to
jointly achieve measurement fidelity and perceptual realism. 1
prNet: Data-Driven Phase Retrieval
via Stochastic Refinement
Mehmet Onurcan Kaya and Figen S. Oktem , Member, IEEE
Abstract—Phase retrieval is an ill-posed inverse problem in
which classical and deep learning–based methods struggle to
jointly achieve measurement fidelity and perceptual realism. Recent works have applied the diffusion framework to phase
retrieval. For instance, DDRM-PR [17], leverages pretrained
diffusion models to solve inverse problems, but its reliance
on generic denoisers that do not learn the forward measurement model limits its adaptability to specific imaging setups.Where the paper says it
Where the paper says it
Where the paper says it
[18] S. Shoushtari, J. p. 2 [44] utilized deep conditional generative
models, such as cGAN and conditional VAE, to solve the
inverse problem of digital holography, showcasing the potential of data-driven approaches in handling optical aberrations. Shoushtari et al.Where the paper says it
[19] M. O. Kaya and F. S. Oktem, “Prnet: Efficient and robust phase retrieval via stochastic refinement,” in 2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP), 2025, pp. p. 0 1
prNet: Data-Driven Phase Retrieval
via Stochastic Refinement
Mehmet Onurcan Kaya and Figen S. Oktem , Member, IEEE
Abstract—Phase retrieval is an ill-posed inverse problem in
which classical and deep learning–based methods struggle to
jointly achieve measurement fidelity and perceptual realism.Where the paper says it
[20] R. W. Gerchberg and W. p. 1 Iterative Projection Techniques for Phase Retrieval
Iterative projection techniques have become fundamental
tools for phase retrieval. One of the earliest and most wellknown algorithms is the classical Gerchberg-Saxton (GS)
algorithm [20], which iteratively applies magnitude constraints
in both the spatial and measurement domains to reconstruct
an unknown signal. Moreover, the flexibility of diffusion models allows their
adaptation to various types of data and measurement settings. Whether dealing with coded diffraction patterns, multi-plane
intensity measurements, or different wavelengths, diffusion
models can be trained to incorporate these variations, enabling
a unified framework for phase retrieval across diverse applications [17], [18].Where the paper says it
Where the paper says it
[21] Y. Shechtman, Y. C. Eldar, O. Cohen, H. N. Chapman, J. Miao, and M. Segev, “Phase retrieval with application to optical imaging: A contemporary overview,” IEEE Signal Processing Magazine, vol. p. 0 Index Terms—Phase retrieval, diffusion models, deep learning,
inverse problems, computational imaging. INTRODUCTION
P
HASE retrieval (PR) is a fundamental inverse problem
in many scientific and engineering disciplines, where the
goal is to reconstruct a signal using only intensity measurements such as Fourier intensities.Where the paper says it
[22] J. Qian, C. Yang, A. Schirotzek, F. Maia, and S. Marchesini, “Efficient algorithms for ptychographic phase retrieval, in inverse problems and applications,” Contemp. p. 5 Given that classical phase retrieval algorithms
can already produce a fairly accurate reconstruction, it is more
efficient to leverage this intermediate solution to avoid wasting
denoiser model capacity on early-stage reconstruction. Such
“image-to-image” rather than “noise-to-image” paradigm has
also been recently exploited for different inverse problems in
imaging [59], [60], [61], [62].Where the paper says it
[23] A. Maiden, D. Johnson, and P. Li, “Further improvements to the ptychographical iterative engine,” Optica, vol. p. 2 [29] attributes this smoothing behavior to
an unavoidable inherent limitation of DNNs in the context of
phase retrieval. However, as long as reconstruction algorithms
prioritize minimizing distortion metrics, such as mean squared
error, we can only expect limited improvements in perceptual
quality.Where the paper says it
[24] M. El Helou and S. Susstrunk, “Blind universal bayesian image denoising with gaussian noise level learning,” IEEE Transactions on Image Processing, vol. p. 5 2, a
well-established framework renowned for its efficacy in image
restoration tasks [64]. Notably, this implementation of UNet
incorporates timestep information as an additional input that
is intricately linked to the noise level of the input image.Where the paper says it
[25] Y. Nishizaki, R. Horisaki, K. Kitaguchi, M. Saito, and J. Tanida, “Analysis of non-iterative phase retrieval based on machine learning,” Optical Review, vol. p. 2 This hybrid approach, which combines neural networks
with analytical methods, has demonstrably succeeded in various real-valued 2D reconstruction problems, including deconvolution, super-resolution, tomography, and phase retrieval
[10], [13], [25]. A key advantage of learning-based direct
inversion methods lies in their low computational complexity
due to their feed-forward (non-iterative) nature, making them
suitable for real-time imaging applications.Where the paper says it
[26] T. Uelwer, A. Oberstrass, and S. Harmeling, “Phase retrieval using conditional generative adversarial networks,” in ICPR, 2020 ref:2507.096084[26]
[27] I. Shevkunov, J. Kilpelainen, and K. Eguiazarian, “Deep convolutional ¨ neural network-based lensless quantitative phase retrieval,” in BiOS, 2021 ref:2507.096084[27]
[28] S. V. Venkatakrishnan, C. A. Bouman, and B. Wohlberg, “Plug-and-play priors for model based reconstruction,” in GlobalSIP, 2013 ref:2507.096084[28]
[29] C¸. Is¸ıl, F. p. 2 As theoretically shown in [14] and
empirically observed in [40], these estimates may deviate
significantly from the natural image manifold, leading to
reconstructions with overly smooth features. Interestingly, the
work by Is¸ıl et al. 1
prNet: Data-Driven Phase Retrieval
via Stochastic Refinement
Mehmet Onurcan Kaya and Figen S. Oktem , Member, IEEE
Abstract—Phase retrieval is an ill-posed inverse problem in
which classical and deep learning–based methods struggle to
jointly achieve measurement fidelity and perceptual realism.Where the paper says it
Where the paper says it
[30] C¸. Is¸ıl and F. S. Oktem, “Model-based phase retrieval with deep denoiser prior,” in COSI, 2020 ref:2507.096084[30]
[31] E. J. Cha, C. Lee, M. Jang, and J. C. Ye, “Deepphasecut: Deep relaxation in phase for unsupervised fourier phase retrieval,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. p. 0 1
prNet: Data-Driven Phase Retrieval
via Stochastic Refinement
Mehmet Onurcan Kaya and Figen S. Oktem , Member, IEEE
Abstract—Phase retrieval is an ill-posed inverse problem in
which classical and deep learning–based methods struggle to
jointly achieve measurement fidelity and perceptual realism.Where the paper says it
[32] Y. Wang, X. Sun, and J. W. Fleischer, “When deep denoising meets iterative phase retrieval,” in ICML, 2020 ref:2507.096084[32]
[33] H. K. Aggarwal, M. P. Mani, and M. Jacob, “Modl: Model-based deep learning architecture for inverse problems,” IEEE Transactions on Medical Imaging, vol. p. 0 In recent years, deep learning has emerged as a powerful
tool for solving various inverse problems in imaging, including
phase retrieval [8], [9]. Data-driven approaches based on
deep neural networks (DNNs) have demonstrated remarkable
success in directly reconstructing images from measurements
or refining initial estimates from classical methods [10].Where the paper says it
[34] V. Monga, Y. Li, and Y. C. Eldar, “Algorithm unrolling: Interpretable, efficient deep learning for signal and image processing,” IEEE Signal Processing Magazine, vol. p. 0 Oktem , Member, IEEE
Abstract—Phase retrieval is an ill-posed inverse problem in
which classical and deep learning–based methods struggle to
jointly achieve measurement fidelity and perceptual realism. We propose a novel framework for phase retrieval that leverages Langevin dynamics to enable efficient posterior sampling,
yielding reconstructions that explicitly balance distortion and
perceptual quality.Where the paper says it
[35] N. Naimipour, S. Khobahi, and M. Soltanalian, “Upr: A model-driven architecture for deep phase retrieval,” ACSSC, 2020 ref:2507.096084[35]
[36] M. Deng, A. Goy, K. Arthur, and G. Barbastathis, “Physics embedded deep neural network for phase retrieval under low photon conditions,” in COSI, 2019 ref:2507.096084[36]
[37] N. Naimipour, S. Khobahi, M. Soltanalian, H. Safavi, and H. C. Shaw, “Unfolded algorithms for deep phase retrieval,” Algorithms, vol. p. 1 Iterative Projection Techniques for Phase Retrieval
Iterative projection techniques have become fundamental
tools for phase retrieval. One of the earliest and most wellknown algorithms is the classical Gerchberg-Saxton (GS)
algorithm [20], which iteratively applies magnitude constraints
in both the spatial and measurement domains to reconstruct
an unknown signal.Where the paper says it
[38] C.-J. Wang, C.-K. Wen, S.-H. L. Tsai, and S. Jin, “Phase retrieval with learning unfolded expectation consistent signal recovery algorithm,” IEEE Signal Processing Letters, vol. p. 1 Iterative Projection Techniques for Phase Retrieval
Iterative projection techniques have become fundamental
tools for phase retrieval. One of the earliest and most wellknown algorithms is the classical Gerchberg-Saxton (GS)
algorithm [20], which iteratively applies magnitude constraints
in both the spatial and measurement domains to reconstruct
an unknown signal.Where the paper says it
[39] A. Liu, X. Fan, Y. Yang, and J. Zhang, “Prista-net: Deep iterative shrinkage thresholding network for coded diffraction patterns phase retrieval,” ArXiv, 2023 ref:2507.096084[39]
[40] C. Ledig et al., “Photo-realistic single image super-resolution using a generative adversarial network,” in CVPR, 2017 ref:2507.096084[40]
[41] K. Tayal, C.-H. Lai, R. Manekar, Z. Zhuang, V. Kumar, and J. Sun, “Unlocking inverse problems using deep learning: Breaking symmetries in phase retrieval,” in NeurIPS 2020 Workshop on Deep Learning and Inverse Problems, 2020 ref:2507.096084[41]
[42] A. G. Dimakis, “Deep generative models and inverse problems,” in Mathematical Aspects of Deep Learning, P. p. 2 Despite these limitations, unrolled learning has
shown success in phase retrieval [35], [36], [37], [38], [39]. Generative Models for Inverse Problems
All of the aforementioned deep learning methods focus
on Maximum A Posteriori or Minimum Mean Squared Error (MMSE) estimation.Where the paper says it
[43] Z. Zhao, J. C. Ye, and Y. Bresler, “Generative models for inverse imaging problems: From mathematical foundations to physics-driven applications,” IEEE Signal Processing Magazine, vol. p. 0 Index Terms—Phase retrieval, diffusion models, deep learning,
inverse problems, computational imaging. INTRODUCTION
P
HASE retrieval (PR) is a fundamental inverse problem
in many scientific and engineering disciplines, where the
goal is to reconstruct a signal using only intensity measurements such as Fourier intensities.Where the paper says it
[44] J. Gladrow, “Digital phase-only holography using deep conditional generative models,” ArXiv, 2019 ref:2507.096084[44]
[45] S. Chan, “Tutorial on diffusion models for imaging and vision,” Foundations and Trends in Computer Graphics and Vision, vol. p. 0 com/METU-SPACE-Lab/prNet-forPhase-Retrieval. Index Terms—Phase retrieval, diffusion models, deep learning,
inverse problems, computational imaging.Where the paper says it
[46] X. Li et al., “Diffusion models for image restoration and enhancement, a comprehensive survey,” ArXiv, 2023 ref:2507.096084[46]
[47] K. Miyasawa, “An empirical bayes estimator of the mean of a normal population,” Bull. p. 3 While computationally efficient,
requiring no modifications to the unconditional pretrained diffusion model’s score function, this approach inherits a fundamental limitation: the initialization does not enforce measurement consistency. Since sampling begins at an intermediate
denoised state (skipping early noise-heavy diffusion steps) yet
still relies on an unconditional score estimator, the generated
samples may diverge from the true data manifold or violate
physical constraints.Where the paper says it
[48] C. Meng et al., “SDEdit: Guided image synthesis and editing with stochastic differential equations,” in ICLR, 2022 ref:2507.096084[48]
[49] C. Saharia, J. Ho, W. Chan, T. Salimans, D. J.
Green — the paper says it, and the page is printed. Red — no passage carries it, so treat that sentence as unverified. The same check runs on your own text: check a summary against its source, $5.
Improvements for AI systems
-
Stochastic Refinement via Langevin Dynamics for Phase Retrieval: The system can perform phase retrieval by leveraging Langevin dynamics to enable efficient posterior sampling, yielding reconstructions that explicitly balance distortion and perceptual quality through a principled combination of stochastic sampling, learned denoising, and model-based updates.
-
Progressive Framework for Model Complexity: The framework comprises three variants of increasing complexity: prNet-Small (theoretically grounded), prNet-Large (parallel reconstruction sampling to approximate the MMSE solution), and prNet-Large-Adv (adversarially trained aggregation network for enhanced perceptual quality).
-
Integration of Hybrid Input-Output Updates: The system can incorporate the Hybrid Input-Output (HIO) algorithm into its updates, which
demonstrates better convergence properties in practice
and allows for the incorporation of object domain constraints such as real-valuedness and non-negativity. -
Test Time Augmentation for Robustness: The system can employ Test Time Augmentation (TTA), including the advanced TTA D4 technique, to enhance reconstruction quality by leveraging inherent invariances of measurement operators and maximizing symmetry properties through averaging over all D4 transformations.
-
Learned Denoising Schedule: The system can learn both noise and denoising schedule during training, allowing the model to
discover an optimal denoising strategy tailored to the reconstruction task,
which improves performance compared to approaches relying on a fixed, predefined diffusion process. -
Adversarial Loss for Perceptual Realism: For prNet-Large-Adversarial, it can incorporate an improved Wasserstein GAN loss with gradient penalty term to enhance perceptual quality alongside distortion metrics, mitigating the
smoothing that are prevalent in other methodologies.
Abstract
Phase retrieval is an ill-posed inverse problem in which existing methods often struggle to balance reconstruction fidelity and perceptual quality. We propose a novel Langevin-based framework for phase retrieval that bridges model-driven and data-driven approaches by combining stochastic posterior sampling, learned denoising, and model-based updates to better navigate the perception-distortion tradeoff. The framework consists of three progressively more advanced variants. The first, prNet-Small, provides a theoretically grounded and lightweight pipeline that integrates Langevin dynamics with learned noise and denoising processes and alternating projection-based updates. Building upon this foundation, prNet-Large exploits parallel sampling of diverse reconstructions and aggregates them to approximate the MMSE solution, significantly improving distortion metrics. Finally, prNet-Large-Adversarial enhances perceptual quality by replacing simple averaging with an adversarially trained aggregation network while preserving reconstruction fidelity. In addition, we incorporate test time augmentation to further improve the performance. Extensive experiments demonstrate that the proposed framework consistently outperforms classical, deep learning-based, and diffusion-based baselines across multiple benchmarks in both reconstruction fidelity and perceptual quality. The source code and trained models are available at https://github.com/METU-SPACE-Lab/prNet-for-Phase-Retrieval
Related papers
- HDNet: High-resolution Dual-domain Learning for Spectral Compressive Imaging
- Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image Reconstruction
- FDIR: Fidelity-Anchored Decompressed Image Restoration for Human and Machine Perception
- A Disease-Centric Vision-Language Foundation Model for Precision Oncology in Kidney Cancer
- CADS: A Comprehensive Anatomical Dataset and Segmentation for Whole-Body Anatomy in Computed Tomography
- Task-Aware Bitrate Thresholds for Codec-Robust Ultrasound Segmentation