只读式超分辨光盘的膜层设计和分析

超分辨技术是一种无需减小记录波长或增大数值孔径而提高存储密度的方法。Ge Sb Te是一种良好的相变光存储材料 ,在超分辨光盘中可作为掩膜。利用多层膜反射率的矩阵法计算了掩膜为Ge2 Sb2 Te5薄膜的超分辨只读式光盘的光学参数与各膜层厚度之间的关系 ,最后得到了较为理想的膜层厚度匹配。采用磁控溅射法制备了只读式超分辨光盘 ,测量了光盘的光学性质。     

基于非下采样Contourlet变换的指纹图像超分辨率重建

非下采样Contourlet变换(Nonsubsampled contourlet transform,NSCT)采用非抽样金字塔结构和非抽样方向滤波器组构成,具有Contourlet变换所不具备的平移不变性、较高冗余度等优良特性,而且能够克服伪吉布斯现象。图像经过非下采样Contourlet变换后分解成多尺度、多方向的细节信息,这些细节信息代表了图像不同频带不同方向的特征,这就简化了系数之间的关系。基于学习的超分辨率重建算法具有整体的预测性,将非下采样Contourlet变换和基于学习的算法相结合,在一定程度上提高训练精度。针对指纹图像的实验证明该算法具有良好的性能,重建的图像纹理性细节信息较好,基本保持了原指纹图像的特征点,更接近于原始的高分辨率图像。     

基于高精度流线生成的交互流场可视化

高效准确的流线绘制一直是流场可视化的重要研究内容,流线可以对流场的重要特征进行有效的稀疏表示,但流线需要长期的粒子追踪过程及大量的积分计算,在面向大规模流场可视化时时间效率较低,需要高性能计算设备进行辅助计算.本文通过设计一种基于深度学习的高精度流线生成算法,将初始的低精度流线快速映射为稠密的高精度流线,可以在较短的时间内快速生成可靠的流线可视化结果,并在此基础上设计了交互式实时流场可视化系统,涵盖了流场的特征检测,属性关联分析,信息论分析等,帮助用户快速了解流场数据,找到自己感兴趣的区域进行后续进一步深度分析,避免了获取过多冗余数据,同时优化了分析工作的效率,满足用户对于流场结构,特征属性等多维度进行关联分析的需求.     

基于密集Inception的单图像超分辨率重建方法

近几年,基于卷积神经网络（CNN）的单图像超分辨率（SR）重建方法成为了主流。通常情况下,重建模型的网络层数越深,提取的特征越多,重建效果越好;然而随着网络层数的加深,不仅会出现梯度消失的问题,还会显著增加参数量,增加训练的难度。针对以上问题,提出了一种基于密集Inception的单图像SR重建方法。该方法引入Inception-残差网络（Inception-ResNet）结构提取图像特征,全局采用简化后的密集网络,且仅构建每一个模块输出到重建层的路径,从而避免产生冗余数据来增加计算量。在放大倍数为4时,采用数据集Set5测试模型性能,结果显示与超深卷积神经网络的图像超分辨率（VDSR）相比,所提方法的结构相似性（SSIM）高了0.013 6;与基于多尺度残差网络的图像SR（MSRN）相比,SSIM高了0.002 9,模型参数量少了78%。实验结果表明,所提方法在保证模型的深度和宽度的情况下,显著减少了参数量,从而降低了训练的难度,而且取得了比对比方法更好的峰值信噪比（PSNR）和SSIM。     

基于ResNeXt和WGAN网络的单图像超分辨率重建

为解决现有基于生成对抗网络的单图像超分辨率重建模型SRGAN网络训练不稳定、学习速率慢等问题,提出了一种基于ResNeXt和WGAN的单图像超分辨率重建模型Res_SRGAN。该模型参考ResNeXt网络结构构造生成器,降低了生成器的复杂度,仅为SRGAN的1/8;通过WGAN来构造判别器解决了SRGAN模型不稳定的问题;实验结果表明,在四个公开数据集上本文所提模型相较于现有的单图像超分辨率重建模型在主客观评价中均取得了更加优越的性能。     

基于非局部算法的序列图像超分辨率重构

提出了一种基于非局部算法的多帧图像超分辨率重构算法,该方法无需进行图像校正。为克服传统图像复原算法基于图像局部点领域的影响,指出可以使用非局部去噪模型的优越边缘保持性和去噪性来重构高分辨率图像。实验证明,该算法在低信噪比情况下,可以取得较好结果,有效解决了低信噪比条件下图像复原的一个难点。     

Progressive spatial-angular feature enhancement network for light field image super-resolution

The intensity and direction of the light field (LF) can be recorded simultaneously by using LF cameras. However, since LF cameras sacrifice spatial resolution for higher angular resolution, the images acquired by LF cameras tend to have low spatial resolution. Therefore, LF image super-resolution (SR) has become an integral part of LF studies. Many existing LF image SR methods fail to fully utilize angular and spatial information due to only using partial sub-aperture images (SAIs). In this paper, we propose a progressive spatial-angular feature enhancement network (PSAFENet) to deal with the problem of missing information in LF image SR. Specifically, we first extract the spatial features of SAIs, the spatial and angular features contained in the macro-pixel images (MacPIs) by three different feature extraction modules. Then, these features are fed into a spatial-angular feature enhancement (SAFE) module to perform enhancement of spatial-angular information on the SAIs. To improve the reconstruction accuracy, we also use the information multi-distillation block (IMDB) to remove the redundant information before upsampling. Our network can well merge the angular and spatial information into each SAI, which facilitates the reconstruction of the LF images. Experimental results on five public datasets show that the proposed PSAFENet method outperforms existing methods in both qualitative and quantitative comparisons.     

Learning knowledge representation with meta knowledge distillation for single image super-resolution

Although the deep CNN-based super-resolution methods have achieved outstanding performance, their memory cost and computational complexity severely limit their practical employment. Knowledge distillation (KD), which can efficiently transfer knowledge from a cumbersome network (teacher) to a compact network (student), has demonstrated its advantages in some computer vision applications. The representation of knowledge is vital for knowledge transferring and student learning, which is generally defined in hand-crafted manners or uses the intermediate features directly. In this paper, we propose a model-agnostic meta knowledge distillation method under the teacher–student architecture for the single image super-resolution task. It provides a more flexible and accurate way to help teachers transmit knowledge in accordance with the abilities of students via knowledge representation networks (KRNets) with learnable parameters. Specifically, the texture-aware dynamic kernels are generated from local information to decompose the distillation problem into texture-wise supervision for further promoting the recovery quality of high-frequency details. In addition, the KRNets are optimized in a meta-learning manner to ensure the knowledge transferring and the student learning are beneficial to improving the reconstructed quality of the student. Experiments conducted on various single image super-resolution datasets demonstrate that our proposed method outperforms existing defined knowledge representation-related distillation methods and can help super-resolution algorithms achieve better reconstruction quality without introducing any extra inference complexity.     

身份保持约束下的面部图像超分辨率重建方法

低分辨率是影响人脸识别精度的重要因素。一种有效方法是使用图像超分辨率技术对低分辨率图像重建,生成超分辨率图像后再对其作人脸识别,从而克服低分辨率面部图像对人脸识别的限制。但是,现有超分辨率方法在重建过程中往往忽略了保持其原始身份信息,这直接影响生成图像的人脸识别结果。针对上述问题,提出了一种身份保持约束下的面部超分辨率重建方法IPNet,在提高低分辨率面部图像质量的同时,能保持重建后的面部图像身份。IPNet方法将语义分割网络和面部生成器相结合,通过语义分割网络提取低维隐码和多分辨率空间特征,进而指导面部生成器输出接近于原图的真实面部图像。在此基础上引入人脸识别网络,将身份信息整合到超分辨率方法中,从而约束重建前后的面部图像身份保持一致。实验结果表明,IPNet方法在超分辨率图像质量和身份保持上均优于其他对比方法。     

聚集诱导发光分子在双光束超分辨光存储中的潜在应用

聚集诱导发光分子因其高效的发光性质而被广泛应用于生物成像、光波导和电致发光等领域,但在光信息存储领域还鲜有研究。与其他光存储材料相比,聚集诱导发光分子的局域密度变化会引发荧光强度的变化,这在光存储领域是一个显著优点。该文针对聚集诱导发光分子的特性,讨论了该类分子在超分辨光存储领域的可能应用方式,以及需要解决的关键问题。