The advance of nanophotonics has provided a variety of avenues for light–matter interaction at the nanometer scale through the enriched mechanisms for physical and chemical reactions induced by nanometer-confined opt...The advance of nanophotonics has provided a variety of avenues for light–matter interaction at the nanometer scale through the enriched mechanisms for physical and chemical reactions induced by nanometer-confined optical probes in nanocomposite materials.These emerging nanophotonic devices and materials have enabled researchers to develop disruptive methods of tremendously increasing the storage capacity of current optical memory.In this paper,we present a review of the recent advancements in nanophotonics-enabled optical storage techniques.Particularly,we offer our perspective of using them as optical storage arrays for next-generation exabyte data centers.展开更多
针对医学影像超分辨率重建过程中细节丢失导致的模糊问题,提出了一种基于深度残差生成对抗网络(GAN)的医学影像超分辨率算法。首先,算法包括生成器网络和判别器网络,生成器网络生成高分辨率图像,判别器网络辨别图像真伪。然后,通过设计...针对医学影像超分辨率重建过程中细节丢失导致的模糊问题,提出了一种基于深度残差生成对抗网络(GAN)的医学影像超分辨率算法。首先,算法包括生成器网络和判别器网络,生成器网络生成高分辨率图像,判别器网络辨别图像真伪。然后,通过设计生成器网络的上采样采用缩放卷积来削弱棋盘效应,并去掉标准残差块中的批量规范化层以优化网络;进一步增加判别器网络中特征图数量以加深网络等方面提高网络性能。最后,用生成损失和判别损失来不断优化网络,指导生成高质量的图像。实验结果表明,对比双线性内插、最近邻插值、双三次插值法、基于深度递归神经网络、基于生成对抗网络的超分辨率方法(SRGAN),所提算法重建出了纹理更丰富、视觉更逼真的图像。相比SRGAN方法,所提算法在峰值信噪比(PSNR)和结构相似度(SSIM)上有0.21 d B和0.32%的提升。所提算法为医学影像超分辨率的理论研究提供了深度残差生成对抗网络的方法,在其实际应用中可靠、有效。展开更多
Single image super-resolution has attracted increasing attention and has a wide range of applications in satellite imaging, medical imaging, computer vision, security surveillance imaging, remote sensing, objection de...Single image super-resolution has attracted increasing attention and has a wide range of applications in satellite imaging, medical imaging, computer vision, security surveillance imaging, remote sensing, objection detection, and recognition. Recently, deep learning techniques have emerged and blossomed, producing " the state-of-the-art” in many domains. Due to their capability in feature extraction and mapping, it is very helpful to predict high-frequency details lost in low-resolution images. In this paper, we give an overview of recent advances in deep learning-based models and methods that have been applied to single image super-resolution tasks. We also summarize, compare and discuss various models from the past and present for comprehensive understanding and finally provide open problems and possible directions for future research.展开更多
基金The authors thank the Australian Research Council for its support through the Laureate Fellowship project(FL100100099).
文摘The advance of nanophotonics has provided a variety of avenues for light–matter interaction at the nanometer scale through the enriched mechanisms for physical and chemical reactions induced by nanometer-confined optical probes in nanocomposite materials.These emerging nanophotonic devices and materials have enabled researchers to develop disruptive methods of tremendously increasing the storage capacity of current optical memory.In this paper,we present a review of the recent advancements in nanophotonics-enabled optical storage techniques.Particularly,we offer our perspective of using them as optical storage arrays for next-generation exabyte data centers.
文摘针对医学影像超分辨率重建过程中细节丢失导致的模糊问题,提出了一种基于深度残差生成对抗网络(GAN)的医学影像超分辨率算法。首先,算法包括生成器网络和判别器网络,生成器网络生成高分辨率图像,判别器网络辨别图像真伪。然后,通过设计生成器网络的上采样采用缩放卷积来削弱棋盘效应,并去掉标准残差块中的批量规范化层以优化网络;进一步增加判别器网络中特征图数量以加深网络等方面提高网络性能。最后,用生成损失和判别损失来不断优化网络,指导生成高质量的图像。实验结果表明,对比双线性内插、最近邻插值、双三次插值法、基于深度递归神经网络、基于生成对抗网络的超分辨率方法(SRGAN),所提算法重建出了纹理更丰富、视觉更逼真的图像。相比SRGAN方法,所提算法在峰值信噪比(PSNR)和结构相似度(SSIM)上有0.21 d B和0.32%的提升。所提算法为医学影像超分辨率的理论研究提供了深度残差生成对抗网络的方法,在其实际应用中可靠、有效。
基金the support from the Shanxi Hundred People Plan of China
文摘Single image super-resolution has attracted increasing attention and has a wide range of applications in satellite imaging, medical imaging, computer vision, security surveillance imaging, remote sensing, objection detection, and recognition. Recently, deep learning techniques have emerged and blossomed, producing " the state-of-the-art” in many domains. Due to their capability in feature extraction and mapping, it is very helpful to predict high-frequency details lost in low-resolution images. In this paper, we give an overview of recent advances in deep learning-based models and methods that have been applied to single image super-resolution tasks. We also summarize, compare and discuss various models from the past and present for comprehensive understanding and finally provide open problems and possible directions for future research.
