摘要翻译：
散粒噪声会影响低光强下成像系统的性能，随着光源功率的减小散粒噪声会变得越来越强。在本文中，我们通过实验证明了使用深度神经网络来恢复弱光下的目标，在等效信噪比方面比经典的Gerchberg-Saxton相位恢复算法有更好的性能。关于目标的先验知识隐式地包含在训练数据集中，对于接近于1的信噪比，特征检测是可能的。我们将这一原理应用于相位恢复问题，并证明了在照明光束中平均每个探测器像素仅有一个光子就成功地恢复了物体的最显著特征。我们还表明，与用原始强度测量训练神经网络相比，用物体的初始估计训练神经网络可以显著地改善相位重建。
---
英文标题：
《Low Photon Count Phase Retrieval Using Deep Learning》
---
作者：
Alexandre Goy, Kwabena Arthur, Shuai Li, George Barbastathis
---
最新提交年份：
2018
---
分类信息：

一级分类：Electrical Engineering and Systems Science        电气工程与系统科学
二级分类：Image and Video Processing        图像和视频处理
分类描述：Theory, algorithms, and architectures for the formation, capture, processing, communication, analysis, and display of images, video, and multidimensional signals in a wide variety of applications. Topics of interest include: mathematical, statistical, and perceptual image and video modeling and representation; linear and nonlinear filtering, de-blurring, enhancement, restoration, and reconstruction from degraded, low-resolution or tomographic data; lossless and lossy compression and coding; segmentation, alignment, and recognition; image rendering, visualization, and printing; computational imaging, including ultrasound, tomographic and magnetic resonance imaging; and image and video analysis, synthesis, storage, search and retrieval.
用于图像、视频和多维信号的形成、捕获、处理、通信、分析和显示的理论、算法和体系结构。感兴趣的主题包括：数学，统计，和感知图像和视频建模和表示；线性和非线性滤波、去模糊、增强、恢复和重建退化、低分辨率或层析数据；无损和有损压缩编码；分割、对齐和识别；图像渲染、可视化和打印；计算成像，包括超声、断层和磁共振成像；以及图像和视频的分析、合成、存储、搜索和检索。
--
一级分类：Physics        物理学
二级分类：Optics        光学
分类描述：Adaptive optics. Astronomical optics. Atmospheric optics. Biomedical optics. Cardinal points. Collimation. Doppler effect. Fiber optics. Fourier optics. Geometrical optics (Gradient index optics. Holography. Infrared optics. Integrated optics. Laser applications. Laser optical systems. Lasers. Light amplification. Light diffraction. Luminescence. Microoptics. Nano optics. Ocean optics. Optical computing. Optical devices. Optical imaging. Optical materials. Optical metrology. Optical microscopy. Optical properties. Optical signal processing. Optical testing techniques. Optical wave propagation. Paraxial optics. Photoabsorption. Photoexcitations. Physical optics. Physiological optics. Quantum optics. Segmented optics. Spectra. Statistical optics. Surface optics. Ultrafast optics. Wave optics. X-ray optics.
自适应光学。天文光学。大气光学。生物医学光学。基本点。准直。多普勒效应。纤维光学。傅里叶光学。几何光学（梯度折射率光学、全息术、红外光学、集成光学、激光应用、激光光学系统、激光、光放大、光衍射、发光、微光学、纳米光学、海洋光学、光学计算、光学器件、光学成像、光学材料、光学计量学、光学显微镜、光学特性、光学信号处理、光学测试技术、光波传播、傍轴光学、光吸收、光激发、物理光学、生理光学、量子光学、分段光学、光谱、统计光学、表面光学、超快光学、波动光学、X射线光学。
--

---
英文摘要：
  Imaging systems' performance at low light intensity is affected by shot noise, which becomes increasingly strong as the power of the light source decreases. In this paper we experimentally demonstrate the use of deep neural networks to recover objects illuminated with weak light and demonstrate better performance than with the classical Gerchberg-Saxton phase retrieval algorithm for equivalent signal over noise ratio. Prior knowledge about the object is implicitly contained in the training data set and feature detection is possible for a signal over noise ratio close to one. We apply this principle to a phase retrieval problem and show successful recovery of the object's most salient features with as little as one photon per detector pixel on average in the illumination beam. We also show that the phase reconstruction is significantly improved by training the neural network with an initial estimate of the object, as opposed as training it with the raw intensity measurement.
---
PDF链接：
https://arxiv.org/pdf/1806.10029