scispace - formally typeset
Search or ask a question
Journal ArticleDOI

Image super-resolution

Linwei Yue1, Huanfeng Shen1, Jie Li1, Qiangqiang Yuan1, Hongyan Zhang1, Liangpei Zhang1 
01 Nov 2016-Signal Processing (Elsevier)-Vol. 128, pp 389-408
TL;DR: This paper aims to provide a review of SR from the perspective of techniques and applications, and especially the main contributions in recent years, and discusses the current obstacles for future research.
About: This article is published in Signal Processing.The article was published on 2016-11-01. It has received 378 citations till now.
Citations
More filters
Journal ArticleDOI
TL;DR: A very deep non-simultaneous fully recurrent convolutional network for video SR is proposed and results demonstrate that the proposed method is better than that of the state-of-the-art SR methods on quantitative visual quality assessment.
Abstract: Video super-resolution (SR) aims at restoring fine details and enhancing visual experience for low-resolution videos. In this paper, we propose a very deep non-simultaneous fully recurrent convolutional network for video SR. To make full use of temporal information, we employ motion compensation, very deep fully recurrent convolutional layers, and late fusion in our system. Residual connection is also employed in our recurrent structure for more accurate SR. Finally, a new model ensemble strategy is used to combine our method with a single-image SR method. Experimental results demonstrate that the proposed method is better than that of the state-of-the-art SR methods on quantitative visual quality assessment.

27 citations


Cites methods from "Image super-resolution"

  • ...According to the differences of images used, image SR can be classified into two categories: single-image SR and multiframe SR [1], [2]....

    [...]

  • ...Single-image SR is mainly constituted of interpolationbased SR and example-based SR [1], [2]....

    [...]

Journal ArticleDOI
TL;DR: The experimental results show that the proposed method significantly outperforms both the bilinear and bicubic interpolations at a very low resolution, and clearly demonstrate the benefit of using trained super-resolution techniques to improve the quality of iris images prior to matching.
Abstract: The lack of resolution has a negative impact on the performance of image-based biometrics. While many generic super-resolution methods have been proposed to restore low-resolution images, they usually aim to enhance their visual appearance. However, an overall visual enhancement of biometric images does not necessarily correlate with a better recognition performance. Reconstruction approaches thus need to incorporate the specific information from the target biometric modality to effectively improve recognition performance. This paper presents a comprehensive survey of iris super-resolution approaches proposed in the literature. We have also adapted an eigen-patches’ reconstruction method based on the principal component analysis eigen-transformation of local image patches. The structure of the iris is exploited by building a patch-position-dependent dictionary. In addition, image patches are restored separately, having their own reconstruction weights. This allows the solution to be locally optimized, helping to preserve local information. To evaluate the algorithm, we degraded the high-resolution images from the CASIA Interval V3 database. Different restorations were considered, with $15\times 15$ pixels being the smallest resolution evaluated. To the best of our knowledge, this is the smallest resolutions employed in the literature. The experimental framework is complemented with six publicly available iris comparators that were used to carry out biometric verification and identification experiments. The experimental results show that the proposed method significantly outperforms both the bilinear and bicubic interpolations at a very low resolution. The performance of a number of comparators attains an impressive equal error rate as low as 5% and a Top-1 accuracy of 77%–84% when considering the iris images of only $15 \times 15$ pixels. These results clearly demonstrate the benefit of using trained super-resolution techniques to improve the quality of iris images prior to matching.

26 citations


Cites background from "Image super-resolution"

  • ...ods [6], [7], such techniques are designed to restore generic images....

    [...]

Journal ArticleDOI
TL;DR: The proposed model differs from existing image variational SR models where the fidelity term is always derived from the L 1 or L 2 - norm, and the regularization term is based on a widely choice of convex and nonconvex functions.
Abstract: The multi-frame super-resolution(SR) aims to recover a high-resolution (HR) image from a degraded low-resolution (LR) sequence. Since the SR problem is considered as an ill-posed one, the regularization techniques are then inevitable. However, the choice of the fidelity and regularization terms is not easy and plays a major role in the quality of the desired HR image. In this paper, we propose a new nonconvex data fitting term and a fractional total variation regularization term for image super-resolution. The proposed model differs from existing image variational SR models where the fidelity term is always derived from the L 1 or L 2 - norm, and the regularization term is based on a widely choice of convex and nonconvex functions. The use of the nonconvex data fitting term can efficiently reduce complex noises such as impulse noise while the fractional order regularization term preserves image features like edges and texture much better. Numerical experiments show that the proposed model can produce competitive results, visually and quantitatively, compared to some available variational SR models.

26 citations

Journal ArticleDOI
TL;DR: An efficient method based on singular value decomposition (SVD) and a mapping model and experiments show that the proposed multi-view face-hallucination scheme is effective and produces promising super-resolved results.

25 citations

Journal ArticleDOI
07 May 2017-Sensors
TL;DR: The application of the SR reconstruction method, including motion estimation and the robust super-resolution technique, to ZY-3 TLC images are introduced and the results show that SR reconstruction can significantly improve both the resolution and image quality of Zy-3TLC images.
Abstract: Super-resolution (SR) image reconstruction is a technique used to recover a high-resolution image using the cumulative information provided by several low-resolution images. With the help of SR techniques, satellite remotely sensed images can be combined to achieve a higher-resolution image, which is especially useful for a two- or three-line camera satellite, e.g., the ZY-3 high-resolution Three Line Camera (TLC) satellite. In this paper, we introduce the application of the SR reconstruction method, including motion estimation and the robust super-resolution technique, to ZY-3 TLC images. The results show that SR reconstruction can significantly improve both the resolution and image quality of ZY-3 TLC images.

23 citations

References
More filters
Journal ArticleDOI
TL;DR: In this article, a structural similarity index is proposed for image quality assessment based on the degradation of structural information, which can be applied to both subjective ratings and objective methods on a database of images compressed with JPEG and JPEG2000.
Abstract: Objective methods for assessing perceptual image quality traditionally attempted to quantify the visibility of errors (differences) between a distorted image and a reference image using a variety of known properties of the human visual system. Under the assumption that human visual perception is highly adapted for extracting structural information from a scene, we introduce an alternative complementary framework for quality assessment based on the degradation of structural information. As a specific example of this concept, we develop a structural similarity index and demonstrate its promise through a set of intuitive examples, as well as comparison to both subjective ratings and state-of-the-art objective methods on a database of images compressed with JPEG and JPEG2000. A MATLAB implementation of the proposed algorithm is available online at http://www.cns.nyu.edu//spl sim/lcv/ssim/.

40,609 citations

Book
23 May 2011
TL;DR: It is argued that the alternating direction method of multipliers is well suited to distributed convex optimization, and in particular to large-scale problems arising in statistics, machine learning, and related areas.
Abstract: Many problems of recent interest in statistics and machine learning can be posed in the framework of convex optimization. Due to the explosion in size and complexity of modern datasets, it is increasingly important to be able to solve problems with a very large number of features or training examples. As a result, both the decentralized collection or storage of these datasets as well as accompanying distributed solution methods are either necessary or at least highly desirable. In this review, we argue that the alternating direction method of multipliers is well suited to distributed convex optimization, and in particular to large-scale problems arising in statistics, machine learning, and related areas. The method was developed in the 1970s, with roots in the 1950s, and is equivalent or closely related to many other algorithms, such as dual decomposition, the method of multipliers, Douglas–Rachford splitting, Spingarn's method of partial inverses, Dykstra's alternating projections, Bregman iterative algorithms for l1 problems, proximal methods, and others. After briefly surveying the theory and history of the algorithm, we discuss applications to a wide variety of statistical and machine learning problems of recent interest, including the lasso, sparse logistic regression, basis pursuit, covariance selection, support vector machines, and many others. We also discuss general distributed optimization, extensions to the nonconvex setting, and efficient implementation, including some details on distributed MPI and Hadoop MapReduce implementations.

17,433 citations

Journal ArticleDOI
TL;DR: It is shown that the elastic net often outperforms the lasso, while enjoying a similar sparsity of representation, and an algorithm called LARS‐EN is proposed for computing elastic net regularization paths efficiently, much like algorithm LARS does for the lamba.
Abstract: Summary. We propose the elastic net, a new regularization and variable selection method. Real world data and a simulation study show that the elastic net often outperforms the lasso, while enjoying a similar sparsity of representation. In addition, the elastic net encourages a grouping effect, where strongly correlated predictors tend to be in or out of the model together.The elastic net is particularly useful when the number of predictors (p) is much bigger than the number of observations (n). By contrast, the lasso is not a very satisfactory variable selection method in the

16,538 citations


"Image super-resolution" refers background in this paper

  • ...As the l2 norm represents a smoothing prior and the l1 norm tends to preserve the edges, the lp ( ≤ ≤ p 1 2) norm achieves a balance between them, thereby avoiding the staircase effect [110]....

    [...]

Journal ArticleDOI
TL;DR: In this article, a constrained optimization type of numerical algorithm for removing noise from images is presented, where the total variation of the image is minimized subject to constraints involving the statistics of the noise.

15,225 citations


"Image super-resolution" refers background in this paper

  • ...[93,103], based on the fact that an image is naturally “blocky” and discontinuous....

    [...]

Book
01 Jan 1977

8,009 citations


"Image super-resolution" refers background in this paper

  • ...In the early years, the smoothness of natural images was mainly considered, which leads to the quadratic property of the regularizations [99,100]....

    [...]