基于深度学习的单像素相机超分辨率成像优化

基于压缩感知和单像素成像的基本原理,设计了一种用于图像超分辨率重建的新型深度卷积神经网络架构.这种单像素超分辨率成像算法成功地将深度学习图像超分辨率重建技术与压缩感知单像素成像技术相结合,从而发展出一种全新的深度学习单像素成像优化方法.与传统的常规压缩感知图像重构算法相比,该算法有效提升了图像超分辨率重建精度和单像素成像质量.通过图像重建的仿真实验和单像素相机的成像实验验证,结果表明这种基于深度学习的新型单像素相机成像方式具有良好的性能表现.     

超分辨率重构

利用低分辨率的图像序列来估计高分辨率图像的方法称为超分辨率图像重建,逐步成为当前科研热点.本文通过POCS视频图像重建算法为例,阐述了超分辨率的概念、应用场合及基本策略和分类,并对超分辨率的重构方法和前景进行了展望.     

基于小波的图像超分辨率重建算法研究

在遥感图像、医学图像等领域，最初获得的图像分辨率往往达不到期望的水平。图像的超分辨率重建就是在低分辨率图像基础上重建出高分辨率图像的技术。针对已有重建算法中的不足，给出一种将高频能量适当降低的SHR重建算法；并进而针对高频细节不能高质量重建的问题，利用小波反变换对高频信息进行重建，提出了一种基于小波高频重建的图像超分辨率重建算法——SHW算法。实验证明，这两种算法的性能比已有图像超分辨率重建算法均有不同程度提高。     

基于振铃抑制的多视频超分辨率重建

为了利用较少低分辨率视频序列实现多视频超分辨率重建,本文提出一种将时空分别进行重建的算法。首先利用已有方法进行时间重建,再以得到的高时间分辨率的视频序列帧为参考帧,结合输入低分辨率视频序列帧进行空间重建。此外,针对传统重建方法在配准不精确的情况下会产生振铃现象这一问题,提出一种加入自适应惩罚项的改进迭代反投影(IBP)算法。实验结果表明,本文算法在输入低分辨率序列较少的情况下,能较好地实现多视频超分辨率重建,且能有效抑制振铃现象;重建出的高分辨率视频序列的结构相似度较对比算法提高3.4%~6.1%;在主观感受上,图像边缘锐利、人工效应少。     

视频监控图像的超分辨率复原研究

超分辨率复原技术是一种可用于提高图像细节辨识能力的有效方法。其在视频监控领域可望得到广泛应用。超分辨率图像处理技术通过融合多帧相似的低分辨率图像达到提高图像细节的目的。从而降低对监控视频采集硬件与后端辅助处理系统的要求,提高对特定目标的辨析能力。本文重点介绍了在视频监控领域较为实用的凸集投影算法、最大后验概率估计算法、基于对象的超分辨率复原方法、基于示例学习与多类预测器的超分辨率复原方法。对以上超分辨率复原方法实现流程的优缺点与其在视频图像监控领域的应用方法进行了相应分析。分析了超分辨率视频监控图像复原常用的基于块匹配与光流的对象运动估计方法。对超分辨率复原重建图像质量的评估标准也进行了相应讨论。     

超分辨率重构

利用低分辨率的图像序列来估计高分辨率图像的方法称为超分辨率图像重建,逐步成为当前科研热点。本文通过POCS视频图像重建算法为例,阐述了超分辨率的概念应用场合及基本策略和分类,并对超分辨率的重构方法和前景进行了展望。     

超分辨率重建技术研究进展

超分辨率(Super Resolution,SR)重建技术是指由一些低分辨率(Low Resolution,LR)模糊的图像或视频序列来估计具有更高分辨率(High Resolution,HR)的图像或视频序列,同时能够消除噪声以及由有限检验器尺寸和光学元件产生的模糊,是提高降质图像或序列分辨率的有效手段。首先介绍超分辨率重建所基于的成像系统模型,并对现有的图像超分辨率重建算法进行总结,重点对基于学习的超分辨重建算法进行对比分析,最后指出超分辨率重建技术的发展方向。     

一种基于子像素配准视频超分辨率重建方法

为了提高视频的空间分辨率,提出了一种利用帧间运动信息进行超分辨率重建的方法。对于整个视频的重建,提出了一种基于滑动窗的分段重建模型。在每一个滑动窗中,首先对相邻帧进行子像素级精度的运动配准;然后通过迭代反投影算法进行超分辨率重建。在配准算法中,提出了一种基于四参数刚体变换模型的配准方法,通过迭代求解和高斯金字塔图像模型由粗及精地进行运动估计。分别对模拟图像及实拍彩色视频进行重建,实验结果表明,该配准算法具有较高的精度,重建算法取得了较高的峰值信噪比(PSNR)值,重建视频具有更好的视觉效果和更高的分辨率能力,可被广泛应用于在帧间主要存在平移和旋转运动的视频序列的超分辨率重建。     

基于结构聚类和字典学习的多帧图像超分辨率重建

提出了一种基于结构聚类和字典学习的超分辨率重建方法,用于多帧或视频图像的高分辨率重建;该方法采用导控核提取图像的局部结构特征,对图像分块进行结构聚类,并通过构建自适应的字典,最终实现稀疏约束重建。给出了实际视频图像的超分辨率重建结果,实验结果验证了本文方法的有效性,且具有较好的重建质量。     

视频超分辨率重建技术综述

在获取视频过程中,有许多因素会导致视频质量的退化,使得视频的空间分辨率降低;而摄像机曝光时间和拍摄帧率又限制了视频的时间分辨率。视频超分辨率重建是一种能有效提高视频时间分辨率和空间分辨率的方法,已经在计算机视觉和图像处理等领域引起了广泛关注。详细阐述了视频超分辨率重建研究的概念和必要性,并较全面地回顾了超分辨率技术近年来的发展历程,对视频超分辨率重建中关键问题进行了较为深入的分析,指出了当今研究难点和今后的研究方向,对视频超分辨率重建的应用前景进行了展望。     

Spatially adaptive block-based super-resolution

Super-resolution technology provides an effective way to increase image resolution by incorporating additional information from successive input images or training samples. Various super-resolution algorithms have been proposed based on different assumptions, and their relative performances can differ in regions of different characteristics within a single image. Based on this observation, an adaptive algorithm is proposed in this paper to integrate a higher level image classification task and a lower level super-resolution process, in which we incorporate reconstruction-based super-resolution algorithms, single-image enhancement, and image/video classification into a single comprehensive framework. The target high-resolution image plane is divided into adaptive-sized blocks, and different suitable super-resolution algorithms are automatically selected for the blocks. Then, a deblocking process is applied to reduce block edge artifacts. A new benchmark is also utilized to measure the performance of super-resolution algorithms. Experimental results with real-life videos indicate encouraging improvements with our method.     

基于Log-WT的人脸图像超分辨率重建

目前已有的基于学习的人脸超分辨率图像重建算法大都对亮度变化特别是阴影非常敏感,针对这一缺点,该文提出了一种不随光照变化的图像表示方法对数-小波变换(Log-WT),并在此基础上构造了一种新的人脸超分辨率图像重建算法。该方法首先利用Log-WT变换提取低分辨率图像与光照无关的内在特性,然后借助流形学习的思想建模高分辨率图像和低分辨率图像之间的关系,并对其加入人脸图像的专用先验约束,从而同时实现了超分辨率重建和图像增强。仿真结果表明该算法有效克服了传统方法受光照因素影响的缺点,在提高图像分辨率的同时克服了光照因素的影响,特别是对阴影效应的消除具有明显效果,将该方法应用于人脸识别,有效提高了识别率。     

连续波太赫兹成像系统的单幅图像超分辨重建

针对现有的太赫兹成像系统所需硬件设备复杂且昂贵的问题,设计了基于单幅图像超分辨重建的连续波太赫兹成像系统,降低设备复杂度和硬件成本。通过对该成像系统生成的太赫兹图像进行双维度预处理,降低图像处理的占用内存,提高后续处理速度。引入限制对比度自适应直方图均衡方法对太赫兹图像进行分区域对比度提升,有效解决太赫兹图像对比度低的问题。利用稀疏表示和字典学习实现太赫兹图像的超分辨重建,提出了反余割拟牛顿平滑零范数的算法解决零范数优化问题,提高了重建精度。通过对该成像系统采集的单幅太赫兹图像进行超分辨重建,在边缘强度上提高了3.232,在平均梯度对比中提高了0.300,验证了对单幅太赫兹图像超分辨重建的有效性与优越性。     

Choice of low resolution sample sets for efficient super-resolution signal reconstruction

In applications such as super-resolution imaging and mosaicking, multiple video sequences are registered to reconstruct video with enhanced resolution. However, not all computed registration is reliable. In addition, not all sequences contribute useful information towards reconstruction from multiple non-uniformly distributed sample sets. In this paper we present two algorithms that can help determine which low resolution sample sets should be combined in order to maximize reconstruction accuracy while minimizing the number of sample sets. The first algorithm computes a confidence measure which is derived as a combination of two objective functions. The second algorithm is an iterative ranked-based method for reconstruction which uses confidence measures to assign priority to sample sets that maximize information gain while minimizing reconstruction error. Experimental results with real and synthetic sequences validate the effectiveness of the proposed algorithms. Application of our work in medical visualization and super-resolution reconstruction of MRI data are also presented.     

图像超分辨率重建算法综述

介绍了超分辨率重建的基本原理与数学模型,对现有的图像超分辨率重建算法进行了总结。将当前的超分辨率算法分为基于重建约束的方法和基于学习的方法两大类,分别阐述了超分辨率重建技术的经典方法,最后指出了低质量图像超分辨率技术进一步的研究方向。     

Image super-resolution via sparse representation over multiple learned dictionaries based on edge sharpness

A new algorithm for single-image super-resolution based on selective sparse representation over a set of coupled dictionary pairs is proposed. Patch sharpness measure for high- and low-resolution patch pairs defined via the magnitude of the gradient operator is shown to be approximately invariant to the patch resolution. This measure is employed in the training stage for clustering the training patch pairs and in the reconstruction stage for model selection. For each cluster, a pair of low- and high-resolution dictionaries is learned. In the reconstruction stage, the sharpness measure of a low-resolution patch is used to select the cluster it belongs to. The sparse coding coefficients of the patch over the selected low-resolution cluster dictionary are calculated. The underlying high-resolution patch is reconstructed by multiplying the high-resolution cluster dictionary with the calculated coefficients. The performance of the proposed algorithm is tested over a set of natural images. PSNR and SSIM results show that the proposed algorithm is competitive with the state-of-the-art super-resolution algorithms. In particular, it significantly out-performs the state-of-the-art algorithms for images with sharp edges and corners. Visual comparison results also support the quantitative results.     

采用双网络结构的压缩视频超分辨率重建

在实际应用中,为了节省带宽和方便存储,图像和视频通常被下采样和压缩,而降质的图像与视频无法满足人们的实际需求。针对这一问题,采用了一种双网络结构的超分辨率重建方法,首先建立下采视频与压缩后的低分辨率视频的映射关系,然后建立质量增强的压缩视频与原始视频的映射关系,最终在输出端可以得到质量提升的视频帧。在网络中,采用密集残差块来提取压缩视频中丰富的局部分层特征,并结合全局残差学习恢复视频中的高频信息。在压缩环节,采用高性能视频编码来验证所提算法的有效性。实验结果表明,相比于主流的视频编码标准和先进的超分辨率重建算法,所提方法能有效提升编码视频的率失真性能。     

Learning adaptive interpolation kernels for fast single-image super resolution

This paper presents a fast single-image super-resolution approach that involves learning multiple adaptive interpolation kernels. Based on the assumptions that each high-resolution image patch can be sparsely represented by several simple image structures and that each structure can be assigned a suitable interpolation kernel, our approach consists of the following steps. First, we cluster the training image patches into several classes and train each class-specific interpolation kernel. Then, for each input low-resolution image patch, we select few suitable kernels of it to make up the final interpolation kernel. Since the proposed approach is mainly based on simple linear algebra computations, its efficiency can be guaranteed. And experimental comparisons with state-of-the-art super-resolution reconstruction algorithms on simulated and real-life examples can validate the performance of our proposed approach.     

Video super-resolution reconstruction based on deep convolutional neural network and spatio-temporal similarity

Existing learning-based super-resolution (SR) reconstruction algorithms are mainly designed for single image, which ignore the spatio-temporal relationship between video frames. Aiming at applying the advantages of learning-based algorithms to video SR field, a novel video SR reconstruction algorithm based on deep convolutional neural network (CNN) and spatio-temporal similarity (STCNN-SR) was proposed in this paper. It is a deep learning method for video SR reconstruction, which considers not only the mapping relationship among associated low-resolution (LR) and high-resolution (HR) image blocks, but also the spatio-temporal non-local complementary and redundant information between adjacent low-resolution video frames. The reconstruction speed can be improved obviously with the pre-trained end-to-end reconstructed coefficients. Moreover, the performance of video SR will be further improved by the optimization process with spatio-temporal similarity. Experimental results demonstrated that the proposed algorithm achieves a competitive SR quality on both subjective and objective evaluations, when compared to other state-of-the-art algorithms.     

基于L曲线的自适应时空正则化视频超分辨率重建

为了解决视频超分辨率重建的病态问题,以得到良好的重建效果,提出了一种新颖的视频超分辨率重建算法。在算法中引入了时空联合正则化算子,通过视频帧本身的空间平滑信息和视频相邻帧的帧间相关先验信息的引入,提高了解的质量;同时,为了选择合适的时空正则化系数,提出了基于L曲线的自适应时空正则化系数计算方法,可以自适应地计算合适的正则化系数。通过对模拟图像序列和真实视频序列的实验结果表明,算法能得到较为精确的解,重建出具有良好视觉效果的高分辨率视频。