基于MAP技术的图像类推超分辨重建方法

在最大后验概率(Maximum A Posterior,MAP)的基础上,结合图像类推(Image Analogies,IA)思想,提出一种序列图像超分辨率重建方法--MAPIA (Maximum A Posterior Image Analogies).该算法先利用传统MAP方法将序列图像进行超分辨率重建,然后在序列图像中选取一帧图像与重建后的图像构造训练集合的图像对,学习它们之间的关系,利用图像类推技术进行超分辨率重建.实验证明文中方法不仅能有效提高图像的清晰度,而且较其它的方法,能得到边缘更加清晰、细节更加突出的重建图像.     

A Probabilistic Framework for Uncertainty-Aware High-Accuracy Precision Grasping of Unknown Objects

Grasping is a fundamental skill for robots which work for manipulation tasks. Grasping of unknown objects remains a big challenge. Precision grasping of unknown objects is even harder. Due to imperfection of sensor measurements and lack of prior knowledge of objects, robots have to handle the uncertainty effectively. In previous work (Chen and Wichert 2015), we use a probabilistic framework to tackle precision grasping of model-based objects. In this paper, we extend the probabilistic framework to tackle the problem of precision grasping of unknown objects. We first propose an object model called probabilistic signed distance function (p-SDF) to represent unknown object surface. p-SDF models measurement uncertainty explicitly and allows measurement from multiple sensors to be fused in real time. Based on the surface representation, we propose a model to evaluate the likelihood of grasp success for antipodal grasps. This model uses four heuristics to model the condition of force closure and perceptual uncertainty. A two step simulated annealing approach is further proposed to search and optimize a precision grasp. We use the object representation as a bridge to unify grasp synthesis and grasp execution. Our grasp execution is performed in a closed-loop, so that robots can actively reduce the uncertainty and react to external perturbations during a grasping process. We perform extensive grasping experiments using real world challenging objects and demonstrate that our method achieves high robustness and accuracy in grasping unknown objects.     

数字图像超分辨率重构技术研究

数字图像超分辨率重建是近20年来兴起的一门新的数字图像处理技术。随着计算机硬件技术和软件设计技术的不断发展,各种数字图像超分辨率重建算法被提出。综述超分辨率重建的相关技术,指出数字图像超分辨率重建技术的未来的发展方向。     

Adam优化的CNN超分辨率重建

为了使单帧图像在不同放大倍数的条件下进行超分辨率重建能得到较好的效果,提出了一种Adam优化的卷积神经网络(convolutional neural network,CNN)超分辨率重建方法。该方法首先使用ISODATA(iterative selforganizing data analysis)聚类算法对训练的图像集进行分类处理,然后在Adam优化的卷积神经网络中对输入图像进行特征提取和非线性映射得到特征映射图,最后在Adam优化的卷积神经网络中对特征映射图进行反卷积重建得到多尺度放大的重建图像。通过实验验证使用该方法在不同放大倍数条件下的重构效果优于传统算法,在视觉效果上有较好的表现。     

视频序列超分辨率重构技术综述

视频序列超分辨率重构技术可以利用来自一个或多个低分辨率视频序列信息重构一个具有高空间分辨率或高时空分辨率的视频序列。本文从视频序列的空间超分辨率、时间超分辨率以及时空超分辨率重构三个方面对视频序列超分辨率重构技术进行了详细的阐述,对视频序列超分辨率重构技术中的关键问题和应用前景进行了分析与展望。     

基于HMRF的自适应超分辨率图像重建算法

在MAP超分辨率图像重建算法中,用Huber-Markov随机场(HMRF)作为图像的先验模型相比于Gaussian-Markov随机场(GMRF)能够更好地保护图像的边缘和细节.在以往的研究中,对于如何选取Huber函数的阈值参数T并没有一个很好的方法.本文提出了一种自适应的MAP超分辨率重建算法,该算法可以自动确定参数T,并根据重建的中间结果,不断对其进行更新,通过迭带最终得到重建图像.实验结果表明,该方法实现了参数的自动选取,在得到期望的高分辨率图像的同时,有效地保护了图像的边缘信息和细节.     

特征子空间规整化的人脸图像超分辨率重建

传统的图像超分辨率(SR)方法中的规整化技术一般用于保持求解过程的数值稳定性以及提供解的平滑性约束,但并不能确保高质量的重建结果.将人脸图像块看作一些特定信号类,利用主成分分析计算训练人脸图像块的特征子空间;并将传统的"重建约束"与人脸图像块的"正交补特征子空间约束"统一在贝叶斯框架下,提出一种人脸图像SR的规整化方法.不局限于以往SR方法中普遍假定的纯平移运动模型的限制,在仿射变换运动模型下提出了3种图像配准与超分辨率重建的联合迭代求解算法.最后通过仿真结果证实了文中方法的有效性.     

Continuous Global Optimization in Multiview 3D Reconstruction

In this article, we introduce a new global optimization method to the field of multiview 3D reconstruction. While global minimization has been proposed in a discrete formulation in form of the maxflow-mincut framework, we suggest the use of a continuous convex relaxation scheme. Specifically, we propose to cast the problem of 3D shape reconstruction as one of minimizing a spatially continuous convex functional. In qualitative and quantitative evaluation we demonstrate several advantages of the proposed continuous formulation over the discrete graph cut solution. Firstly, geometric properties such as weighted boundary length and surface area are represented in a numerically consistent manner: The continuous convex relaxation assures that the algorithm does not suffer from metrication errors in the sense that the reconstruction converges to the continuous solution as the spatial resolution is increased. Moreover, memory requirements are reduced, allowing for globally optimal reconstructions at higher resolutions. We study three different energy models for multiview reconstruction, which are based on a common variational template unifying regional volumetric terms and on-surface photoconsistency. The three models use data measurements at increasing levels of sophistication. While the first two approaches are based on a classical silhouette-based volume subdivision, the third one relies on stereo information to define regional costs. Furthermore, this scheme is exploited to compute a precise photoconsistency measure as opposed to the classical estimation. All three models are compared on standard data sets demonstrating their advantages and shortcomings. For the third one, which gives the most accurate results, a more exhaustive qualitative and quantitative evaluation is presented.     

基于MG-GMRES算法的图像超分辨率重建

提出了一种基于多层网格(MG)和广义极小残余(GMRES)算法相结合的图像超分辨率重建快速算法.首先采用正则化方法给出图像超分辨率重建模型;然后在系统介绍MG和GMRES算法的基础上,针对图像超分辨率重建中非对称线性稀疏方程的求解,提出多层网格-广义极小残余(MG-GMRES)算法;详细讨论了MG-GMRES算法的光滑、限制、插值操作以及计算复杂度.实验研究表明该算法的重建结果相当有效,与MG、GMRES和Richrdson迭代相比,具有更快的收敛速度.     

基于小波域隐马尔可夫模型的信号超分辨率重建

提出一种基于小波域隐马尔可夫模型(WHMM)的信号超分辨率重建算法。根据贝叶斯原理和最大后验概率估计理论,将WHMM作为先验知识给出一般信号的超分辨率重建模型;详细推导了重建问题的Euler-La-grange方程及对数似然函数的导数计算,将信号的超分辨率重建归结为一个简单线性方程组的求解;最后采用期望最大化(EM)算法和共轭梯度算法交替迭代计算WHMM的模型参数和高分辨率重建信号。一维和二维测试信号的实验结果表明该方法在有效抑制噪声的同时,能够很好地重建出信号的高频细节。在相同的信号降质条件下,针对一维情形,本文重建方法的峰值信噪比(PSNR)较三次插值和Tikhonov正则化方法平均提高2.3994 dB和4.474 2 dB;针对二维情形,本文重建方法的PSNR较双三次插值和Tikhonov正则化方法平均提高1.1741 dB和0.648 7 dB。     

基于正则化的超分辨率图像重建方法及其实现

超分辨率图像重建是用同一景物的若干低分辨率图像通过数字图像处理技术获取其高分辨率图像的一种技术.介绍了基于正则化方法的超分辨率图像重建的研究现状和以正则化为基础的几种重建方法在近几年的研究和发展趋势.在此基础上,实现了一种遥感图像的正则化超分辨率重建算法,实验验证了方法的有效性.     

Single Image Super-Resolution Reconstruction Technique based on A Single Hybrid Dictionary

A new sparse domain approach is proposed in this paper to realize the single image super-resolution (SR) reconstruction based upon one single hybrid dictionary, which is deduced from the mixture of both the high resolution (HR) image patch samples and the low resolution (LR) ones. Moreover, a linear model is proposed to characterize the relationship between the sparse representations of both the HR image patches and the corresponding LR ones over the same hybrid dictionary. It is shown that, the requirement on the identical sparse representation of both HR and LR image patches over the corresponding HR dictionary and the LR dictionary can be relaxed. It is unveiled that, the use of one single hybrid dictionary can not only provide a more flexible framework to keep the similar sparse characteristics between the HR patches and the corresponding degenerated LR patches, but also to accommodate their differences. On this basis, the sparse domain based SR reconstruction problem is reformulated. Moreover, the proposed linear model between the sparse representations of both the HR patch and the corresponding LR patch over the same hybrid dictionary offers us a new method to interpret the image degeneration characteristics in sparse domain. Finally, practical experimental results are presented to test and verify the proposed SR approach.     

基于图像配准的POCS超分辨率图像重构

图像重构是数字图像处理的一个重要的分支,根据图像序列进行重构的高分辨率图像在多种应用邻域得以应用。该文简要介绍了图像成像原理以及降阶模型,并提出在图像配准的基础上,对图像序列采用POCS方法高分辨率重构,将图像校准算法和POCS方法有机地结合在一起,同时给出了其中详细的算法和实现过程。实验仿真结果表明该算法当图像间平移量小于10个象素、旋转角小于5时收敛,且运算量小,收敛速度快,具有很好的图像超分辨率重构能力。     

Robust Wavelet-Based Super-Resolution Reconstruction: Theory and Algorithm

We present an analysis and algorithm for the problem of super-resolution imaging, that is the reconstruction of HR (high-resolution) images from a sequence of LR (low-resolution) images. Super-resolution reconstruction entails solutions to two problems. One is the alignment of image frames. The other is the reconstruction of a HR image from multiple aligned LR images. Both are important for the performance of super-resolution imaging. Image alignment is addressed with a new batch algorithm, which simultaneously estimates the homographies between multiple image frames by enforcing the surface normal vectors to be the same. This approach can handle longer video sequences quite well. Reconstruction is addressed with a wavelet-based iterative reconstruction algorithm with an efficient de-noising scheme. The technique is based on a new analysis of video formation. At a high level our method could be described as a better-conditioned iterative back projection scheme with an efficient regularization criteria in each iteration step. Experiments with both simulated and real data demonstrate that our approach has better performance than existing super-resolution methods. It can remove even large amounts of mixed noise without creating artifacts.     

正电子发射层析成像的鲁棒最小二乘重建

提出的鲁棒最小二乘算法综合考虑了正电子发射层析成像中的各种误差,适用于实际正电子发射层析成像系统．实验结果表明：该算法比传统的最小二乘重建算法具有更加鲁棒的重建特性．     

超分辨率图像复原中的快速L-曲线估计

讨论了从一组低采样降质的视频图像重建超分辨率图像中未知参数的估计问题．使用L-Curve标准来估计正则化参数，然而，L-Curve的计算代价十分昂贵．它需要计算正则化近似解和残差的范式．为此提出一种基于Lanczos算法和Gauss积分理论的算法，在超分辨率图像重建中的参数估计中可以减少L-Curve的计算代价．     

基于自适应多字典对的超分辨率复原算法

最近,双字典训练已成为在计算机视觉和图像领域解决超分辨率复原问题的有力工具。针对基于双字典训练的图像超分辨率算法中字典训练与重构阶段的重构误差,提出了一种基于自适应多字典对的超分辨
　　率复原算法。通过对样本进行聚类并训练多特征字典来适应不同类型的输入图像。在字典训练阶段,充分利用了不同次训练字典产生的差异,在重建中筛选高频补丁,进行多次重构,有效地提升了重构图像的质量。实验仿真与比较表明,该方法在重构图像的质量上有所提高,且能提供更清晰的细节。     

生成式对抗网络在超分辨率图像重建中的应用

针对现有卷积神经网络图像超分辨率算法容易出现过拟合、损失函数的收敛性不足等问题,结合超分辨率算法和生成式对抗网络(GAN)理论,设计一种基于生成式对抗网络的超分辨率算法PESRGAN用于恢复四倍下采样的图像。首先使用残差密集块(RDB)作为基本结构单元,有效避免了过拟合问题;其次使用双层特征损失并使用渗透指数(PI)作为损失的权值,更好地去学习低分辨率到高分辨率图像之间的映射关系;同时使用VGG19作为判别网络高分辨率图像进行分类;最后使用经典数据集,将PESRGAN算法与双三次插值(Bicubic)、SRGAN、ESRGAN算法在客观参数和主观视觉效果进行对比。实验结果表明:在经典数据集上,PESRGAN的平均峰值信噪比(PSNR)达到25.4 dB、平均结构相似性(SSIM)达到0.73,平均渗透指数(PI)达到1.15,在客观参数和主观评价上均优于其他算法,证明了PESRGAN有良好的超分辨率重建的效果。     

Super-Resolution image Reconstruction Based on Iteration and Wavelet Transform

In this paper, we provide a super-resolution image reconstruction algorithm based on wavelet transform. Wavelet transform can separate high frequency and low frequency information of image. The more high frequency information can be obtained by using wavelet transform and the technique of image fusion. Meanwhile, reconstructed super-resolution image is produced by the iterative method. In iteration process, noise of image can be suppressed by applying method of wavelet threshold de-noising. The experiment results show that the algorithm can overcome the disadvantage of the classical interpolation method and effectively improve the resolution and PSNR of the image.