HIONet: Deep priors based deep unfolded network for phase retrieval

Yang, Yuchi; Lian, Qiusheng; Zhang, Xiaohua; Zhang, Dan; Zhang, Huibin

doi:10.1016/j.dsp.2022.103797

Cited by 4 publications

(3 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…and Expt. : 400 and 140 pairs l 2 -norm Yang et al 206 Intensity Phase CNN in space and frequency domain Sim. : 400 and 60,000 pairs l 2 -norm and edge loss “---” indicates not available …”

Section: Dl-in-processing For Phase Recoverymentioning

confidence: 99%

“…Wu et al 205 integrated the Fresnel forward operator and TIE inverse model into a neural network, which can be efficiently trained with a small number of datasets and is suitable for transfer learning. Yang et al 206 unrolled the classic HIO algorithm into a neural network that combines information both in the spatial domain and frequency domain. Since PiN-based networks are embedded with physical knowledge, good performance can usually be achieved with a small training dataset.…”

Section: Dl-in-processing For Phase Recoverymentioning

confidence: 99%

See 1 more Smart Citation

On the use of deep learning for phase recovery

Wang,

Song,

Wang

et al. 2024

Light Sci Appl

View full text Add to dashboard Cite

Phase recovery (PR) refers to calculating the phase of the light field from its intensity measurements. As exemplified from quantitative phase imaging and coherent diffraction imaging to adaptive optics, PR is essential for reconstructing the refractive index distribution or topography of an object and correcting the aberration of an imaging system. In recent years, deep learning (DL), often implemented through deep neural networks, has provided unprecedented support for computational imaging, leading to more efficient solutions for various PR problems. In this review, we first briefly introduce conventional methods for PR. Then, we review how DL provides support for PR from the following three stages, namely, pre-processing, in-processing, and post-processing. We also review how DL is used in phase image processing. Finally, we summarize the work in DL for PR and provide an outlook on how to better use DL to improve the reliability and efficiency of PR. Furthermore, we present a live-updating resource (https://github.com/kqwang/phase-recovery) for readers to learn more about PR.

show abstract

Section: Dl-in-processing For Phase Recoverymentioning

confidence: 99%

Section: Dl-in-processing For Phase Recoverymentioning

confidence: 99%

On the use of deep learning for phase recovery

Wang,

Song,

Wang

et al. 2024

Light Sci Appl

View full text Add to dashboard Cite

show abstract

“…For instance, the Wirtinger Flow (WF) 14 algorithm essentially utilizes gradient descent and reconstructs the signal by iteratively updating the initial estimated signal. Deep learning methods 15,16 attempt to learn more complex and advanced priors information from large amounts of paired data, which is different from relying on artificially designed priors. The plug-and-play (PnP) 17,18 approach inserts advanced denoisers into iterative optimization algorithms to solve nonconvex optimization problems in phase retrieval problems.…”

Section: Introductionmentioning

confidence: 99%

Real-time snapshot fractional Fourier phase retrieval via deep unfolding network

Zhiyi Zhang,

Yixiao Yang,

Ran Tao

2024

Sixth Conference on Frontiers in Optical Imaging and Technology: Novel Imaging Systems

View full text Add to dashboard Cite

Phase retrieval aims at recovering phase information from intensity observation patterns and realizing the reconstruction of images, which plays an important role in computational imaging. Recently, the near-field observation and reconstruction paradigm represented by fractional Fourier phase retrieval has broken through the limitations of traditional Fourier phase retrieval and realized single-shot phasing. However, existing reconstruction algorithms are mainly based on an optimized iterative framework that requires multiple iterations and relies on both accurate forward and backward projection, and thus cannot be applied to the fractional Fourier fast algorithm that lacks inverse transformations. So it limits the possibilities of real-time imaging to some extent. To address this challenge, this paper proposes a deep unfolding network, which introduces the fast fractional Fourier transform unfolded from an optimization iteration process. Through end-to-end training, the network can correct the error due to the inaccuracy of the inverse transform, achieving fast convergence and effective reconstruction. Experimental results show that the proposed method can utilize the fast fractional Fourier transform to achieve real-time snapshot phase retrieval.

show abstract

Speckle autocorrelation separation method based on frequency intensity for tracking moving object beyond optical memory effect

Shi,

Cui,

Liu

et al. 2024

J. Opt.

View full text Add to dashboard Cite

Imaging objects behind a scattering medium beyond the optical memory effect range is vital in various imaging scenarios. Despite numerous proposed imaging methods aimed at separating objects, effectively tracking moving objects remains challenging. In this paper, we present a non-invasive scattering imaging method to reconstruct target beyond the optical memory effect range and track moving objects using a speckle separation and position estimation technique. A speckle autocorrelation separation method based on frequency intensity is proposed to eliminate the noise from the cross-correlation and to separate the objects from the mixed speckles. A position estimation technique is proposed to determine the positional relationships of the objects using speckle deconvolution using the point spread function of imaging regions. A non-invasive imaging system is designed to track the moving object without prior knowledge of the shape and distribution of objects. Experimental validation shows the efficiency of the method for separation and localization, allowing for the reconstruction of the target behind the scattering medium and tracking of the moving object behind the scattering medium. Moreover, the method is capable of separating and tracking a moving object when multiple objects are in the background.

show abstract

HIONet: Deep priors based deep unfolded network for phase retrieval

Cited by 4 publications

References 30 publications

On the use of deep learning for phase recovery

On the use of deep learning for phase recovery

Real-time snapshot fractional Fourier phase retrieval via deep unfolding network

Speckle autocorrelation separation method based on frequency intensity for tracking moving object beyond optical memory effect

Contact Info

Product

Resources

About