A nonlinear least square technique for simultaneous image registration and super-resolution.

This paper proposes a new algorithm to integrate image registration into image super-resolution (SR). Image SR is a process to reconstruct a high-resolution (HR) image by fusing multiple low-resolution (LR) images. A critical step in image SR is accurate registration of the LR images or, in other words, effective estimation of motion parameters. Conventional SR algorithms assume either the estimated motion parameters by existing registration methods to be error-free or the motion parameters are known a priori. This assumption, however, is impractical in many applications, as most existing registration algorithms still experience various degrees of errors, and the motion parameters among the LR images are generally unknown a priori. In view of this, this paper presents a new framework that performs simultaneous image registration and HR image reconstruction. As opposed to other current methods that treat image registration and HR reconstruction as disjoint processes, the new framework enables image registration and HR reconstruction to be estimated simultaneously and improved progressively. Further, unlike most algorithms that focus on the translational motion model, the proposed method adopts a more generic motion model that includes both translation as well as rotation. An iterative scheme is developed to solve the arising nonlinear least squares problem. Experimental results show that the proposed method is effective in performing image registration and SR for simulated as well as real-life images.     

Video super resolution based on non-local regularization and reliable motion estimation

Video super-resolution (SR) is a process for reconstructing high-resolution (HR) images by utilizing complementary information among multiple low-resolution (LR) images. Accurate estimation of the motion among the LR images significantly affects the quality of the reconstructed HR image. In this paper, we analyze the possible reasons for the inaccuracy of motion estimation and then propose a multi-lateral filter to regularize the process of motion estimation. This filter can adaptively correct motion estimation according to the estimation reliability, image intensity discontinuity, and motion dissimilarity. Furthermore, we introduce a non-local prior to solve the ill-posed problem of HR image reconstruction. This prior can fully utilize the self-similarities existing in natural images to regularize the HR image reconstruction. Finally, we employ a Bayesian formulation to incorporate the two regularizations into one Maximum a Posteriori (MAP) estimation model, where the HR image and the motion estimation can be refined progressively in an alternative and iterative manner. In addition, an algorithm that estimates the blur kernel by analyzing edges in an image is also presented in this paper. Experimental results demonstrate that the proposed approaches are highly effective and compare favorably to state-of-the-art SR algorithms.     

压缩视频超分辨率重建技术

超分辨率图像重建就是由低分辨率图像序列来估计高分辨率图像,而压缩视频的重建正成为当前研究的热点。本文首先分析了压缩视频重建的基础,建立了高、低分辨率图像间的关系,给出了量化噪声和运动矢量的模型;接着对目前最具有代表性的最大后验概率(MAP)算法、凸集投影(POCS)算法和迭代反向投影(IBP)算法进行了详细的阐述,并分别给出了实验结果;然后分析了运算的复杂度,介绍了几种实时化方法;最后针对目前存在的问题进行了展望,指出降质模型、运动估计、重建算法和实时应用将是今后研究的重点。     

Correlation estimation from compressed images

This paper addresses the problem of correlation estimation in sets of compressed images. We consider a framework where the images are represented under the form of linear measurements due to low complexity sensing or security requirements. We assume that the images are correlated through the displacement of visual objects due to motion or viewpoint change and the correlation is effectively represented by optical flow or motion field models. The correlation is estimated in the compressed domain by jointly processing the linear measurements. We first show that the correlated images can be efficiently related using a linear operator. Using this linear relationship we then describe the dependencies between images in the compressed domain. We further cast a regularized optimization problem where the correlation is estimated in order to satisfy both data consistency and motion smoothness objectives with a Graph Cut algorithm. We analyze in detail the correlation estimation performance and quantify the penalty due to image compression. Extensive experiments in stereo and video imaging applications show that our novel solution stays competitive with methods that implement complex image reconstruction steps prior to correlation estimation. We finally use the estimated correlation in a novel joint image reconstruction scheme that is based on an optimization problem with sparsity priors on the reconstructed images. Additional experiments show that our correlation estimation algorithm leads to an effective reconstruction of pairs of images in distributed image coding schemes that outperform independent reconstruction algorithms by 2–4 dB.     

Region-based super-resolution for compression

Every user of multimedia technology expects good image and video visual quality independently of the particular characteristics of the receiver or the communication networks employed. Unfortunately, due to factors like processing power limitations and channel capabilities, images or video sequences are often downsampled and/or transmitted or stored at low bitrates, resulting in a degradation of their final visual quality. In this paper, we propose a region-based framework for intentionally introducing downsampling of the high resolution (HR) image sequences before compression and then utilizing super resolution (SR) techniques for generating an HR video sequence at the decoder. Segmentation is performed at the encoder on groups of images to classify their blocks into three different types according to their motion and texture. The obtained segmentation is used to define the downsampling process at the encoder and it is encoded and provided to the decoder as side information in order to guide the SR process. All the components of the proposed framework are analyzed in detail. A particular implementation of it is described and tested experimentally. The experimental results validate the usefulness of the proposed method.     

Generative bayesian image super resolution with natural image prior

We propose a new single image super resolution (SR) algorithm via Bayesian modeling with a natural image prior modeled by a high-order Markov random field (MRF). SR is one of the long-standing and active topics in image processing community. It is of great use in many practical applications, such as astronomical observation, medical imaging, and the adaptation of low-resolution contents onto high-resolution displays. One category of the conventional approaches for image SR is formulating the problem with Bayesian modeling techniques and then obtaining its maximum-a-posteriori solution, which actually boils down to a regularized regression task. Although straightforward, this approach cannot exploit the full potential offered by the probabilistic modeling, as only the posterior mode is sought. On the other hand, current Bayesian SR approaches using the posterior mean estimation typically use very simple prior models for natural images to ensure the computational tractability. In this paper, we present a Bayesian image SR approach with a flexible high-order MRF model as the prior for natural images. The minimum mean square error (MMSE) criteria are used for estimating the HR image. A Markov chain Monte Carlo-based sampling algorithm is presented for obtaining the MMSE solution. The proposed method cannot only enjoy the benefits offered by the flexible prior, but also has the advantage of making use of the probabilistic modeling to perform a posterior mean estimation, thus is less sensitive to the local minima problem as the MAP solution. Experimental results indicate that the proposed method can generate competitive or better results than state-of-the-art SR algorithms.     

基于一阶范数的视频超分辨率重建

讨论了视频成像的基本模型,并在此基础上提出了一种基于一阶范数的视频图像重建算法,该方法同时对高分辨率图像和运动矢量进行迭代估计,并采用一阶范数和Robers算子对于当前普遍的采用二阶范数项作为视频数据逼近项和归整项的方式进行了改进。实验结果表明,该算法在原图像受到椒盐噪声影响的情况下,重建效果要优于二阶方法,并且该方法在重建图象的边缘保持上也有相对比较好的效果。     

Noniterative interpolation-based super-resolution minimizing aliasing in the reconstructed image

Super-resolution (SR) techniques produce a high-resolution image from a set of low-resolution undersampled images. In this paper, we propose a new method for super-resolution that uses sampling theory concepts to derive a noniterative SR algorithm. We first raise the issue of the validity of the data model usually assumed in SR, pointing out that it imposes a band-limited reconstructed image plus a certain type of noise. We propose a sampling theory framework with a prefiltering step that allows us to work with more general data models and also a specific new method for SR that uses Delaunay triangulation and B-splines to build the super-resolved image. The proposed method is noniterative and well posed. We prove its effectiveness against traditional iterative and noniterative SR methods on synthetic and real data. Additionally, we also prove that we can first solve the interpolation problem and then make the deblurring not only when the motion is translational but also when there are rotations and shifts and the imaging system Point Spread Function (PSF) is rotationally symmetric.     

Super-resolution mosaicing from MPEG compressed video

In this paper we address the problem of mosaic construction from MPEG 1/2 compressed video for the purpose of video browsing. State-of-the-art mosaicing methods work on raw video, but most video content is available in compressed form such as MPEG 1/2. Applying these methods to compressed video requires full decoding which is very costly. The resulting mosaic is in general too large to display on the screen and is thus inappropriate for the purpose of video browsing. Therefore, we directly extract very low-resolution frames from MPEG 1/2 compressed video for the mosaic construction and then apply a super-resolution (SR) method based on iterative backprojections in order to increase the mosaic resolution and its visual quality. Global motion to be used in the SR method for aligning and warping the frames is estimated from motion information contained in the compressed stream. We also use the estimated global motion in the blur estimation and in the choice of the degradation model used for the restoration in the SR algorithm. The method for the SR mosaic construction from MPEG 1/2 compressed video that we present in this paper is less costly than mosaic construction from full decoded video. Furthermore, the resulting mosaic size is more appropriate for the purpose of video browsing.     

Commutability of blur and affine warping in super-resolution with application to joint estimation of triple-coupled variables

This paper proposes a new approach to the image blind super-resolution (BSR) problem in the case of affine interframe motion. Although the tasks of image registration, blur identification, and high-resolution (HR) image reconstruction are coupled in the imaging process, when dealing with nonisometric interframe motion or without the exact knowledge of the blurring process, classic SR techniques generally have to tackle them (maybe in some combinations) separately. The main difficulty is that state-of-the-art deconvolution methods cannot be straightforwardly generalized to cope with the space-variant motion. We prove that the operators of affine warping and blur commute with some additional transforms and derive an equivalent form of the BSR observation model. Using this equivalent form, we develop an iterative algorithm to jointly estimate the triple-coupled variables, i.e., the motion parameters, blur kernels, and HR image. Experiments on synthetic and real-life images illustrate the performance of the proposed technique in modeling the space-variant degradation process and restoring local textures.     

Image super-resolution by textural context constrained visual vocabulary

Example-based super-resolution (SR) approach hallucinates the missing high-resolution (HR) details by learning the example image patches. This approach implicitly assumes that the similarity of the low-resolution (LR) patches can infer the similarity of the corresponding HR patches. However, this similarity preserving assumption may not be held in practice. Thus the example-based super-resolved image inevitably contains artifacts not close to the ground truth. In this paper, we propose a novel single-image SR method by integrating an enforced similarity preserving process by using visual vocabulary into example-based SR approach. By jointly learning the HR and LR visual vocabularies, we can obtain a geometric co-occurrence prior to make the geometric similarity preserved within each visual word. We further propose a two-step framework for SR. The first step estimates the optimum visual word using textural context cue while the second step enforces the visual word subspace constraint and reconstruction constraint for estimating the final result. Experiments demonstrate the effectiveness of our method for recovering the missing HR details, especially texture.     

A Mixed Non-local Prior Model for Image Super-resolution Reconstruction

Generating high-resolution image from a set of degraded low-resolution images is a challenge prob-lem in image processing. Due to the ill-posed nature of Super-resolution (SR), it is necessary to find an eff ective image prior model to make it well-posed. For this pur-pose, we propose a mixed non-local prior model by adap-tively combining the non-local total variation and non-local H1 models, and establish a multi-frame SR method based on this mixed non-local prior model. The unknown High-resolution (HR) image, motion parameters and hyper-parameters related to the new prior model and noise statis-tics are determined automatically, resulting in an unsu-pervised super-resolution method. Extensive experiments demonstrate the eff ectiveness of the proposed SR method, which can not only preserve image details better but also suppress noise better.     

Multiframe super-resolution based on half-quadratic prior with artifacts suppress

The multiframe super-resolution (SR) technique aims to obtain a high-resolution (HR) image by using a set of observed low-resolution (LR) images. In the reconstruction process, artifacts may be possibly produced due to the noise, especially in presence of stronger noise. In order to suppress artifacts while preserving discontinuities of images, in this paper a multiframe SR method is proposed by involving the reconstruction properties of the half-quadratic prior model together with the quadratic prior model using a convex combination. Moreover, by analyzing local features of the underlined HR image, these two prior models are combined by using an automatically calculated weight function, making both smooth and discontinuous pixels handled properly. A variational Bayesian inference (VBF) based algorithm is designed to efficiently and effectively seek the solution of the proposed method. With the VBF framework, motion parameters and hyper-parameters are all determined automatically, leading to an unsupervised SR method. The efficiency of the hybrid prior model is demonstrated theoretically and practically, which shows that our SR method can obtain better results from LR images even with stronger noise. Extensive experiments on several visual data have demonstrated the efficacy and superior performance of the proposed algorithm, which can not only preserve image details but also suppress artifacts.     

Bayesian Separation of Images Modeled With MRFs Using MCMC

We investigate the source separation problem of random fields within a Bayesian framework. The Bayesian formulation enables the incorporation of prior image models in the estimation of sources. Due to the intractability of the analytical solution, we resort to numerical methods for the joint maximization of the a posteriori distribution of the unknown variables and parameters. We construct the prior densities of pixels using Markov random fields based on a statistical model of the gradient image, and we use a fully Bayesian method with modified-Gibbs sampling. We contrast our work to approximate Bayesian solutions such as iterated conditional modes (ICM) and to non-Bayesian solutions of ICA variety. The performance of the method is tested on synthetic mixtures of texture images and astrophysical images under various noise scenarios. The proposed method is shown to outperform significantly both its approximate Bayesian and non-Bayesian competitors.     

Super-resolution reconstruction of compressed video using transform-domain statistics

Considerable attention has been directed to the problem of producing high-resolution video and still images from multiple low-resolution images. This multiframe reconstruction, also known as super-resolution reconstruction, is beginning to be applied to compressed video. Super-resolution techniques that have been designed for raw (i.e., uncompressed) video may not be effective when applied to compressed video because they do not incorporate the compression process into their models. The compression process introduces quantization error, which is the dominant source of error in some cases. In this paper, we propose a stochastic framework where quantization information as well as other statistical information about additive noise and image prior can be utilized effectively.     

Learning Sparse Overcomplete Codes for Images

Images can be coded accurately using a sparse set of vectors from a learned overcomplete dictionary, with potential applications in image compression and feature selection for pattern recognition. We present a survey of algorithms that perform dictionary learning and sparse coding and make three contributions. First, we compare our overcomplete dictionary learning algorithm (FOCUSS-CNDL) with overcomplete independent component analysis (ICA). Second, noting that once a dictionary has been learned in a given domain the problem becomes one of choosing the vectors to form an accurate, sparse representation, we compare a recently developed algorithm (sparse Bayesian learning with adjustable variance Gaussians, SBL-AVG) to well known methods of subset selection: matching pursuit and FOCUSS. Third, noting that in some cases it may be necessary to find a non-negative sparse coding, we present a modified version of the FOCUSS algorithm that can find such non-negative codings. Efficient parallel implementations in VLSI could make these algorithms more practical for many applications.     

Multi-objective super resolution: concepts and examples

Described methods for simultaneously generating the super-resolved depth map and the image from LR observations. Structural information is embedded within the observations and, through the two formulations of DFD and SFS problems, we were able to generate the super-resolved images and the structures. The first method described here avoids correspondence and warping problems inherent in current SR techniques involving the motion cue in the LR observations and uses a more natural depth-related defocus as a natural cue in real aperture imaging. The second method, while again avoiding the correspondence problems, also demonstrates the usefulness of the generalized interpolation scheme leading to more flexibility in the final SR image, in the sense that the LR image can be viewed at SR with an arbitrary light source position. The quality of the super-resolved depth and intensity maps has been found to be quite good. The MAP-MRF framework that was used in both methods models both the surface normal and the intensity field as separate MRFs, and this helps in regularizing the solution.     

Bayesian inference of models and hyperparameters for robust optical-flow estimation

Selecting optimal models and hyperparameters is crucial for accurate optical-flow estimation. This paper provides a solution to the problem in a generic Bayesian framework. The method is based on a conditional model linking the image intensity function, the unknown velocity field, hyperparameters, and the prior and likelihood motion models. Inference is performed on each of the three levels of this so-defined hierarchical model by maximization of marginalized a posteriori probability distribution functions. In particular, the first level is used to achieve motion estimation in a classical a posteriori scheme. By marginalizing out the motion variable, the second level enables to infer regularization coefficients and hyperparameters of non-Gaussian M-estimators commonly used in robust statistics. The last level of the hierarchy is used for selection of the likelihood and prior motion models conditioned to the image data. The method is evaluated on image sequences of fluid flows and from the "Middlebury" database. Experiments prove that applying the proposed inference strategy yields better results than manually tuning smoothing parameters or discontinuity preserving cost functions of the state-of-the-art methods.     

A MAP approach for joint motion estimation, segmentation, and super resolution.

Super resolution image reconstruction allows the recovery of a high-resolution (HR) image from several low-resolution images that are noisy, blurred, and down sampled. In this paper, we present a joint formulation for a complex super-resolution problem in which the scenes contain multiple independently moving objects. This formulation is built upon the maximum a posteriori (MAP) framework, which judiciously combines motion estimation, segmentation, and super resolution together. A cyclic coordinate descent optimization procedure is used to solve the MAP formulation, in which the motion fields, segmentation fields, and HR images are found in an alternate manner given the two others, respectively. Specifically, the gradient-based methods are employed to solve the HR image and motion fields, and an iterated conditional mode optimization method to obtain the segmentation fields. The proposed algorithm has been tested using a synthetic image sequence, the "Mobile and Calendar" sequence, and the original "Motorcycle and Car" sequence. The experiment results and error analyses verify the efficacy of this algorithm.     

A generalized model for Kalman filtering of motion information in video compression

In this paper, we tackle the problem of motion estimation in video compression. Since Full Search Algorithms (FSA) present the disadvantage of adding a high computational burden to the encoder, fast search techniques have been used in conjunction with predictive filtering, in such a way to guarantee an acceptable quality with an affordable complexity. The aim of this work is to propose a novel framework for Kalman filtering of motion information in compressed video sequences. The merits of our new framework are twofold: First, using an appropriate formulation of the system equations, several shortcomings inherent with former models in the literature are greatly counteracted. Secondly, it is constructed using a generalized structure in such a way to enclose a large variety of prediction models. Therefore, it can adapt to different types of motion activities in video sequences, without the need for a different formulation in each prediction model, as was the case in previous studies. Furthermore, we propose an adaptive motion compensation technique that permits an additional improvement to the decoded video quality. Our framework permits a considerable gain in the average performance compared to previous models and even to the FSA technique.