Speckle noise reduction in coherent imaging based on deep learning without clean data

Yin, Da; Gu, Zhongzheng; Zhang, Yanran; Gu, Fengyan; Nie, Shouping; Feng, Shuai; Ma, Jun; Chen, Yuan

doi:10.1016/j.optlaseng.2020.106151

Cited by 35 publications

(13 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The neural network is specifically designed to operate in a hologram-inhologram-out manner; the data format of both input and output is set to a 6-channel 2D image, which a stack of real and imaginary parts of a 3-channel color hologram. Whereas most denoising algorithms are applied to reconstructed 2D focal images [22][23][24][25][26] or intermediate light field representations [27],…”

Section: Deep Learning-based Incoherent Holographic Cameramentioning

confidence: 99%

Towards holographic streaming systems: From real-time acquisition of the real world to holographic display

Kim

Yang

et al. 2022

Preprint

View full text Add to dashboard Cite

While recent progress in holographic displays has shown that they are capable of displaying photorealistic 3D holograms in real time, the acquisition of high-quality real-world holograms has remained a missing piece regarding the realization of holographic streaming systems. Incoherent holographic cameras, which record holograms under daylight conditions, are suitable candidates for real-world acquisition, as they avoid the safety issue involved in the use of laser lights; however, they are hindered by severe noise due to the optical imperfections of such systems. In this work, we develop a deep learning-based incoherent holographic camera system that can deliver visually enhanced holograms in real time. A neural network filters the noise in the captured holograms, maintaining a complex-valued hologram format throughout the whole process. Enabled by the computational efficiency of the proposed filtering strategy, we demonstrate the first holographic streaming system integrating a holographic camera and a holographic display, with the aim of developing the ultimate holographic ecosystem of the future.

show abstract

Section: Deep Learning-based Incoherent Holographic Cameramentioning

confidence: 99%

Towards holographic streaming systems: From real-time acquisition of the real world to holographic display

Kim

Yang

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Finally, the model used a data argumentation [85,86] for effective learning. Another research by Tian et al [87] proposed a deep learning method based on U-Net [73] and Noise2Noise [88] method. First, the noise was validated on computer-generated holography (CGH) images.…”

Section: Cnn Denoising For Specific Imagesmentioning

confidence: 99%

Methods for image denoising using convolutional neural network: a review

Ilesanmi

2021

Complex Intell. Syst.

196

View full text Add to dashboard Cite

Image denoising faces significant challenges, arising from the sources of noise. Specifically, Gaussian, impulse, salt, pepper, and speckle noise are complicated sources of noise in imaging. Convolutional neural network (CNN) has increasingly received attention in image denoising task. Several CNN methods for denoising images have been studied. These methods used different datasets for evaluation. In this paper, we offer an elaborate study on different CNN techniques used in image denoising. Different CNN methods for image denoising were categorized and analyzed. Popular datasets used for evaluating CNN image denoising methods were investigated. Several CNN image denoising papers were selected for review and analysis. Motivations and principles of CNN methods were outlined. Some state-of-the-arts CNN image denoising methods were depicted in graphical forms, while other methods were elaborately explained. We proposed a review of image denoising with CNN. Previous and recent papers on image denoising with CNN were selected. Potential challenges and directions for future research were equally fully explicated.

show abstract

“…The image processing methods mainly adopt the filtering idea, according to the theory of information optics, considering the differences between the distribution and characteristics of object and noise in the signal domain. At present, they are divided into the space-domain filtering-based (Darakis and Soraghan, 2006;Shortt et al, 2006;Uzan et al, 2013), transform-domain filtering-based (Maycock et al, 2007;Sharma et al, 2008;Choi et al, 2010), and deep learning-based methods (Zhang et al, 2017;Jeon et al, 2018;Wang et al, 2019;Montresor et al, 2020;Yin et al, 2020). Especially, the deep learning-based methods have achieved excellent performance over the traditional algorithms as soon as they appeared (Di et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

Coherent Noise Suppression of Single-Shot Digital Holographic Phase Via an Untrained Self-Supervised Network

Tang

Zhang

et al. 2022

Front. Photon.

View full text Add to dashboard Cite

In digital holography, the coherent noise affects the measurement accuracy and reliability greatly due to the high spatial and temporal coherence of the laser. Especially, compared with the speckle noise of intensity in digital holography, the coherent noise of phase contains more medium- and low-frequency characteristics, which hinders the effectiveness of noise suppression algorithms. Here, we propose a single-shot untrained self-supervised network (SUSNet) for the coherent noise suppression of phase, requiring only one noisy phase map to complete the optimization and learning. The SUSNet can smoothen and suppress the background fluctuations, parasitic fringes, and diffraction loops in a noisy phase and shows good generalization performance for samples with different shapes, sizes, and phase ranges. Compared with the traditional algorithms and the ground truth-supervised neural network (DnCNN), the SUSNet has the best noise suppression performance and background smoothing effect. As a result, the SUSNet can suppress the fluctuation range to ∼20% of the original range.

show abstract

Speckle noise reduction in coherent imaging based on deep learning without clean data

Cited by 35 publications

References 29 publications

Towards holographic streaming systems: From real-time acquisition of the real world to holographic display

Towards holographic streaming systems: From real-time acquisition of the real world to holographic display

Methods for image denoising using convolutional neural network: a review

Coherent Noise Suppression of Single-Shot Digital Holographic Phase Via an Untrained Self-Supervised Network

Contact Info

Product

Resources

About