 Research
 Open Access
 Published:
TV2++: a novel spatialtemporal total variation for super resolution with exponentialtype norm
EURASIP Journal on Wireless Communications and Networking volume 2020, Article number: 223 (2020)
Abstract
Recently, many superresolution algorithms have been proposed to recover highresolution images to improve visualization and help better analyze images. Among them, total variation regularization (TV) methods have been proven to have a good effect in retaining image edge information. However, these TV methods do not consider the temporal correlation between images. Our algorithm designs a new TV regularization (TV2++) to take advantage of the time dimension information of the images, further improving the utilization of useful information in the images. In addition, the union of global low rank regularization and TV regularization further enhances the image superresolution recovery. And we extend the exponentialtype penalty (ETP) function on singular values of a matrix to enhance lowrank matrix recovery. A novel image superresolution algorithm based on the ETP norm and TV2++ regularization is proposed. And the alternating direction method of multipliers (ADMM) is applied to solve the optimization problems effectively. Numerous experimental results prove that the proposed algorithm is superior to other algorithms.
Introduction
The superresolution technology [1–4] is to restore highfrequency details lost during hardware acquisition of images, thereby improving image quality, making the image more rich in texture and providing better visualization. Superresolution technology is widely applied to face recognition [1], CT diagnosis [2], highdefinition television [3], remote sensing image [4, 5], etc. These studies based on image processing are of great significance to the construction of the Internet of Things (IoT) [6] and smart cities. Although SR technology has been researched and improved a lot, its efficiency is still far from the requirements of realtime applications. The research and implementation of cloud computing [7] provides new ideas for the improvement of SR technology. Unfortunately, the system based on cloud environment has many shortcomings [8, 9].
At present, the mainstream of superresolution algorithms can be divided into two types of categories, namely, the reconstructionbased methods [10–13] and the learningbased methods [14–17]. Recently, learningbased methods have gained huge attentions because of its efficiency and generalization. The learningbased methods acquire the cooccurrence prior knowledge between the lowresolution and highresolution image blocks through the learning process. From sparse representation [15, 18], anchored neighborhood regression [16] to later transformed selfexemplars [17, 19] and deep convolutional networks [20–22], by learning from examples based on huge databases consisting of lowresolution and highresolution image pairs, these methods can recover details and enhance texture information. Extracting the high frequency information based on local features from the training images and then adding the high frequency detail for lowresolution image can guide a highresolution image reconstruction [14]; however, it also results that these methods deeply rely on selected data and sometimes may bring some artifacts. Moreover, learningbased methods usually require a large number of training sets and a large amount of time to complete the training, which makes it impossible to meet the requirements in real time. Because the model relies too heavily on the data set, it does not have independence [17, 19]. A lot of time and pretreatment also make this method inefficient so that it cannot achieve the desired effect. The edge calculation based on big data [23, 24] can improve the processing efficiency of the system model to a certain extent. We propose to use ADMM to optimize the calculation of the model, which greatly improves the running speed and efficiency.
Conversely, the bulk of reconstructed based methods usually get highresolution image from a sequence of lowresolution images by optimizing the cost function which have prior restriction [10]. The reconstruction based methods are to invert highresolution images from the lowresolution image through the image degradation model, which is to solve the inverse problem of the image, and often requires prior knowledge of gradient [25], sparse [15, 26, 27], spatialtemporal feature [28, 29] and so on. Iterative back projection method (IP) proposed by Pejman et al. [11] obtained the highresolution image through iterative back projection for deviation of simulated lowresolution image and observed image. Nonlocal means (NLM) [12, 24] is a SR method based on the nonlocal property. It explains that analogous pixels are not limited to a local area, such as long edges and texture structures. As seen in [13, 30], a framework of maximum a posteriori (MAP) estimation is proposed to performs joint blur identification and highresolution image reconstruction. And the algorithm addresses blind image super resolution by fusing multiple blurred lowresolution images to render a highresolution image. In recent years, many popular superresolution algorithms based on total variation regularization (TV) [10, 31–34] have emerged through reconstruction perspective. The TV function is usually defined as the integral of absolute value of image gradient, as shown in [31, 35]; the total variation of the signal is used as a regularizing functional. Since the signal with too much and possibly false details has a high total variation, i.e., the integral of the absolute gradient of the signal is high. According to this principle, the total variation of the signal is reduced to closely match the original signal, removing unnecessary details while retaining important details such as edges. In the case of low signaltonoise ratio, total variation denoising is also very effective in retaining edges while smoothing out noise in flat areas. This also leads to a total deterioration that will make the restored image too smooth, and in some more detailed images, the restored image will lose details. Therefore, it is the focus of research to keep more details while removing noise.Farsiu et al [33,36] proposed a bilateral total variation (BTV) regularization prior algorithm, which used the same smoothing coefficient to process adjacent pixels at the same position, and smoothed the images in all directions while retaining certain edge information. In [5,37], the authors formulated a new time dependent convolutional model for super resolution based on the TV regularization. And in [38], a spatially weighted TV image superresolution algorithm is proposed, in which the spatial information distributed in different image regions is added to constrain the superresolution process. In addition, Li et al. [39] further improved the above algorithm based on TV regularization. They proposed a new regularization term named steering kernel regression total variation (SKRTV), in which the local structural regularity properties can be fully exploited. Furthermore, in [32,40], a partial differential equation (PDE) model is proposed for SR based on a constrained variational model which uses the nonlocal total variation (NLTV) as a regularization term. As known from these algorithms, TV regularization has a good effect on retaining image edge information [36,41].
However, these TVbased regularization methods act only on the space dimension and does not take into account the dependence of the time dimension [42,43]. And there are many images with temporal similarities between frames, such as sequence images [44] and medical CT images [45,46]. In addition, for the time dimension in TV regularization, Li et al. [47] proposed that one can directly treat the time component as an additional space variable and form the corresponding seminorm. In this form, all dimensions are coupled, and the expected behavior is uniform in all directions.The time component is directly regarded as a spatial variable, which ignores the similarity in the time dimension and the difference between the temporal variable and the spatial variable. Without considering time and space separately, picture details and edge information will be ignored. Therefore, considering the differing behaviors of the spatial and temporal components, we decouple the spatial dimensions from the temporal one when constructing TV2++. Moreover, TV2++ could allow for more flexibility in penalizing. Admittedly, TV regularization is so susceptible to noise that often causes staircase effects. To weaken this flaw, we added a global lowrank constraint on the image, as Feng et al. [10] did. The global lowrank constraint in the model is to enhance global consistency and improve noise immunity. In addition, we introduce the exponentialtype penalty (ETP) norm [48] to constrain the image with lowrank. Nonconvex penalty functions such as ETP are extended on singular values of a matrix as surrogate functions of norm to enhance lowrank matrix recovery more effectively, which has been proven in [49]. The ETP is characterized by a positive parameter, which establishes a connection with the ℓ0 and ℓ1 penalties.
In this paper, we introduce the ETP global lowrank regularization [48,50] and design a TV regularization on the space dimension and the time dimension (TV2++) to construct the basic framework of the algorithm. Overall, our contributions are threefold:

The algorithm, which designs TV2++ regularization based on spatiotemporal, utilizes image time dimension similarity and further strengthens image detail recovery.

A novel framework based on TV2++ regularization and ETP norm lowrank regularization is constructed; TV2++ regularization helps retain image edge information; ETP norm lowrank regularization does well in global consistency and improving noise immunity.

We use an efficient alternating direction method of multipliers (ADMM) [51]based approach for problem optimization.
Background
In this part, we first introduce a basic model in the TV methods, and then we introduce the exponentialtype penalty function and IRNN algorithm for solving the nonconvex lowrank minimization problem.
Basic model
We first suggest the basic model in the TV methods. In this model, we take noise and blur into consideration. Then, we solve the SR problem through this model. The basic observation model is:
where T means the image we observed and X is the HR image we expect to recover. D symbolizes the downsampling operator and S is the blurring operator. At the same time, N represents the noise which influencing our observation results.
We want the HR image to be as perfect as possible.In mathematics, we can get the optimal solution in the basic model. So, we deform the above model to build a new cost function as follows:
When we solve the optimization problem, then we can get the optimal X, which we can define as X_{0}. The cost function consist of one penalizing term about LR image T and HR image X.
To better solve this illposed problem, we can add regularization terms.
where ρ(X) means the regularization term. This term usually depends on prior knowledge and we will illustrate this term in the following part. λ is the parament controlling the weigh of regularization terms in the whole model.
Nonconvex lowrank minimization
Variable selection problems are typically addressed under a penalized optimization framework. Nonconvex penalties such as the exponentialtype penalty (ETP) [48,52] have been demonstrated to have the properties of sparsity practically and theoretically. The exponentialtype penalty is characterized by a positive parameter, which establishes a connection with the and penalties. More specifically,the limits of ETP are the ℓ0 and ℓ1 penalties when this parameter approaches ∞ and 0 respectively. And it is easy to extend the exponentialtype penalty functions on singular values of a matrix as surrogate functions of norm to enhance lowrank matrix recovery. In addition, matrix completion algorithm [53] is based on the assumption that recovered matrix has low rank and then the missing entries can be filled in by minimizing the difference between the input matrix and the estimated one.
However, different from convex optimization, solving the nonconvex lowrank minimization problem is much more challenging than the nonconvex sparse minimization problem. Iteratively reweighted least squares (IRLS) algorithm [54] has been recently extended to handle the nonconvex Schattenp norm penalty. Actually, it solves a relaxed smooth problem which may require many iterations to achieve a lowrank solution. It cannot solve the general nonsmooth problem.
Recently, Lu et al. [49] propose an iteratively reweighted nuclear norm (IRNN) algorithm to solve the nonconvex nonsmooth lowrank minimization problem. The IRNN algorithm takes advantage of the following properties of exponentialtype penalty function: the exponentialtype penalty function is concave and monotonically increasing on [0,∞], and its gradient is a decreasing function. IRNN algorithm iteratively solves a weighted singular value thresholding (WSVT) problem. By setting the weight vector as the gradient of the concave penalty function, the WSVT problem has a closed form solution.
where w is the weight coefficient, σ is the singular value, and ∇f(X^{k}) is the super gradient.
Our method
In this part, we will propose our own model, namely LRTV2++. As we know, rank is the important property, often calculated by the minimum of columns and rows containing nonzero elements. Rank is often thought about the richness of information contained in images. In regularization, if a matrix has low rank property, we can recover some losing columns or rows linearly expressed by some known rows and columns. This theory is widely used in matrix completion. We often represent the low rank function about matrix X from the certain norm, in this paper, we use ETP function to approximate L_{0} norm.
where X is the number of dimensions, and α_{i} is the weigh. Especially, α_{i} satisfies two constraints:
Gao et al. [17] proposed a nonconvex continuous surrogate function called exponential type penalty (ETP), as follows:
And its super gradient is defined as:
As we know, TV function on the vertical horizontal is usually defined as:
where Ω is spatial domain, and Ω⊆R^{2}. And then, we consider temporal dependency and get the difference term of the time dimension ∂_{t}X. Its formula is as follows:
Therefore, TV2++ can be expressed as:
The first of Eq. (11)is the spatial regularization term, and the latter is the temporal regularization term. Then, adding the ETP low rank regularization and TV2++ regularization, the superresolution reconstruction model can be further expressed as:
In this method, we separate ∂_{t}X from ∂_{x}X and ∂_{y}X, separating spatial dimensions from temporal dimensions, considering the difference of the temporal dimension and spatial dimensions.
The optimization
To solve the optimization problem of the cost function Eq. (11), we use the alternating direction method of multipliers (ADMM) algorithm. ADMM is proved to be an efficient algorithm and a widely used optimization method for constrained problems when a cost function includes multiple variables. This algorithm solve one variable through other dual variables and iterate this variable to solve other variables. Repeat this process, then we can complete the optimization problem of our cost functions. We will show how to use ADMM to optimize our cost functions in the following contents.
where M and U are the auxiliary variables. Further derivation of Eq. (13), the augmented Lagrangian function can be obtained as follows:
Subproblem 1: updating X
equivalent to:
Take the derivative of the above function :
From Eq. (17), we can easily get the equation of X in TV2++ method:
Subproblem 2: updating M
equivalent to:
It can be further transformed into:
where,
As we all know, a globally optimal solution to the above problem is given by the weighted singular value thresholding:
where,
Eq. (24) is the SVD of Y.
Subproblem 3: update U
equivalent to:
which can be solved efficiently via a soft shrinkage operator:
where,
Experimental results and analysis
We take CT images of the HNSCC3DCTRT dataset as original images to perform the experiment. And the lowresolution images are all obtained by MATLAB simulation. There are four comparison algorithms used in the experiment: L1TV, L2TV, NLM [12], and LRTV [10]. In addition, we employed two important characters to estimate the recovery quality: peak signaltonoise ratio (PSNR) and structure similarity index (SSIM). PSNR is widely used to evaluate quality of SR recovery and its unit is decibels (dB). The mathematical formula of PSNR is defined as:
where MSE is the mean square error between original HR image and recovered HR image. Aside from PSNR, SSIM is another important character we used to evaluate the similarity between images. SSIM is usually considered to accord with the visual perception of human naked eyes. Its mathematical formula can be written as:
where μ_{x} is the average value of the original HR image x and μ_{y} is the average value of the recovered y, σ_{x} is the variance of x and σ_{x} is the variance of y. σ_{xy} is the covariance of original HR image and recovered image. c_{1} and c_{2} are the balance parameters. SSIM is ranged from 0 to 1. When the recovered image is exactly same to original HR image, SSIM equals 1.
Performance under noise environment
In this part, we add Gaussian noise to the images (4HEADNECK 2.0 B30s50686) in order to test the robustness of superresolution reconstruction. Gaussian noise is a special kind of noise whose probability density function obeys normal distribution. We set mean of Gaussian noise to be 0 and its variance to be 0.001, 0.003, 0.005, 0.006, 0.007. Each algorithm is tested in the same experimental environment, and the experimental results are shown in curves charts.
Figure 1 and Fig. 2 show the PSNR and SSIM trends for all algorithm results as the variance of Gaussian noise increases from 0.001 to 0.007, where sigma represents the variance of the Gaussian noise. In Fig. 1 and Fig. 2, we can see that the proposed method has overwhelmingly advantage compared with other algorithms. When sigma increased gradually, the advantage tends to emerge. We can find that the index data curve of the proposed algorithm is much better than the others, which means that the proposed algorithm has better image superresolution recovery ability.
Figure 3 shows recovered images of different methods and enlarged regions. Compared to original HR image, recovered images of L1TV, L2TV, and NLM appear to be blurred while the recovered image of the proposed method is clearer and the details are better restored. This is because we enhance the efficiency of low rank regular terms by replacing the tracking norm with ETP nonconvex penalty function constraints. In addition, the TV2++ regular term utilizes the temporal dimensional similarity of the image to further enhance the detail recovery capability of the image.
Recovery performance comparison
In this part, we will use more medical images from our dataset and show results by using different methods. We mainly show two other CT images in different part of bodies to evaluate the recovery performance of our proposed methods. We first chose one 3D CT of 12082009RTHEADNECK Adult25471 series. By using the above methods, we will put results and recovered image and closeup view of selected regions in each image in the following part for comparison. From the Table 1, we can see that the proposed method gets best PSNR and SSIM index values. The recovered images and details in selected location are shown in Fig. 4. We can find that the result of the proposed method is clearer than other methods.
When we compare these results to original image, we also find the proposed method is more similar to original image, resulting in high SSIM.
We further chose HEADNECK CT images to test and verify experimental results in the subsequent part. Processed images are shown in Fig. 5. We also show specific data of their PSNR and SSIM in the Table 2.
We also tested other images in our database and got similar results to what we show by testing two examples. In general, the proposed method gets highest SSIM and PSNR than all other comparison methods. In addition, under blur interference, our proposed method is clearer than other methods.By selecting a closeup view of the location, this method displays the details better than other methods.
Ablation analysis
We use adult images 4HEADNECK 2.0 B30s50686 as the test image for parameter optimization experiments. For the parameter of lowrank term, we set \(\alpha _{1}=\alpha _{2}=\frac {1}{2}\), which means weigh controlling each matrix unfolded in each dimensions plays the same role. We estimate the error for each iteration by calculating ∥X^{k}−X^{k}−1∥. When the above error is less than 1e−5, we stop the optimization of the parameters.
First, we set λ_{2} to 0.0001. We experiment with λ_{2} being set between 0.0001 and 0.1, respectively. Through running our observed Fig. 6, it can be seen that the value of λ_{1} is near 0.001 when the PSNR reaches a peak. Continuing to increase the value of λ_{1}, the PSNR shows a monotonous decreasing trend. As can be seen from Fig. 7, when λ_{1} increases between intervals 0 and 0.1, the value of SSIM shows a tendency to decrease slightly. Taking into account the performance of the above indicators, we believe that the experimental result obtained is the best when the value of λ_{1} is set to 0.009.
Then, we fixed the parameter λ_{1} and performed a parameter optimization experiment on the parameter λ_{2}. We experiment with λ_{2} being set between 0.0001 and 0.1, respectively. Through running our program, we acquire the value of PSNR and SSIM when λ_{2} is 0.0001, 0.0002, 0.0005, 0.0007, 0.01, 0.1, and 0.5. And the line charts are shown in Fig. 8 and Fig. 9.
As can be seen from Fig. 8, the line chart has both a rising interval and a falling interval, and when λ_{2} is around 0.1, the PSNR value reaches a peak. For the SSIM in Fig. 9, it can be seen that as λ_{2} increases, the value of SSIM continues to decrease. Taking into account the performance of the above indicators, we believe that the experimental result obtained is the best when the value of λ_{2} is set to 0.1.
Discussion
In this paper, we propose a superresolution reconstruction algorithm based on TV2++ regularization and ETP norm lowrank regularization and optimize it by ADMM method. TV2++ regularization is based on spatiotemporal and utilizes image time dimension similarity. Considering the differing behaviors of the spatial and temporal components, we decouple the spatial dimensions from the temporal one which also allows for more flexibility in penalizing. On the other hand, ETP norm are extended on singular values of a matrix as surrogate functions of L_{0}norm to enhance lowrank matrix recovery more effectively. Then, the experimental results reveals that the proposed method has better capacity of resisting noise and blur. In addition, our model is more complex than NLM, L1TV, and L2TV, although we use the ADMM algorithm for optimization. But it still takes more time than NLM, L1TV, and L2TV. The reason may be that the program takes a lot of time to solve the TV problem.
Availability of data and materials
Not applicable
Abbreviations
 TV:

Total variation
 ETP:

Exponentialtype penalty
 ADMM:

Alternating direction method of multipliers
 CT:

Computed tomography
 IBP:

Iterative back projection method
 NLM:

Nonlocal means
 MAP:

Maximum a posteriori
 BTV:

Bilateral total variation
 SKRTV:

Steering kernel regression total variation
 PDE:

Partial differential equation
 NLTV:

Nonlocal total variation
 SR:

Superresolution
 HR:

High resolution
 LR:

Low resolution
 IRLS:

Iteratively reweighted least squares
 IRNN:

Iteratively reweighted nuclear norm
 WSVT:

Weighted singular value thresholding
 SVD:

Singular value decomposition
 MATLAB:

Matrix laboratory
 L1TV:

L1 norm and total variation
 L2TV:

L2 norm and total variation
 LRTV:

Lowrank and total variation
 PSNR:

Peak signaltonoise ratio
 SSIM:

Structure similarity index
 dB:

Decibels
 MSE:

Mean square error
References
 1
J. Jiang, R. Hu, Z. Han, Z. Wang, Lowresolution and lowquality face superresolution in monitoring scene via supportdriven sparse coding. J Signal Proc. Syst.75(3), 245–256 (2014). doi:10.1007/s1126501308049.
 2
C. You, Y. Zhang, X. Zhang, G. Li, S. Ju, Z. Zhao, Z. Zhang, W. Cong, P. K. Saha, G. Wang, CT superresolution GAN constrained by the identical, residual, and cycle learning ensemble (GANCIRCLE). IEEE Trans. Med. Imaging. 39(1), 188–203 (2019). doi:10.1109/TMI.2019.2922960.
 3
M. Sugie, S. Gohshi, H. Takeshita, C. Mori, in 2014 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS). Subjective assessment of superresolution 4k video using paired comparison, (2014), pp. 042–047. doi:10.1109/ISPACS.2014.7024422.
 4
Z. Pan, J. Yu, H. Huang, S. Hu, A. Zhang, H. Ma, W. Sun, Superresolution based on compressive sensing and structural selfsimilarity for remote sensing images. IEEE Trans. Geosci. Remote Sens.51(9), 4864–4876 (2013). doi:10.1109/TGRS.2012.2230270.
 5
G. Xu, S. Khan, H. Zhu, L. Han, M. K. Ng, H. Yan, Discriminative tracking via supervised tensor learning. Neurocomputing. 315:, 33–47 (2018). doi:10.1016/j.neucom.2018.05.108.
 6
J. Zhou, J. Sun, P. Cong, Z. Liu, S. Hu, Securitycritical energyaware task scheduling for heterogeneous realtime MPSoCs in IoT. IEEE Trans. Serv. Comput.13(4), 745–758 (2020). doi:10.1109/TSC.2019.2963301.
 7
X. Xu, R. Mo, F. Dai, W. Lin, S. Wan, W. Dou, Dynamic resource provisioning with fault tolerance for dataintensive meteorological workflows in cloud. IEEE Trans. Ind. Inform.16(9), 6172–6181 (2020). doi:10.1109/TII.2019.2959258.
 8
L. Qi, Y. Chen, Y. Yuan, S. Fu, X. Xu, A QoSaware virtual machine scheduling method for energy conservation in cloudbased cyberphysical systems. World Wide Web. 23(2), 1275–1297 (2020). doi:10.1007/s1128001900684y.
 9
Y. Xu, L. Qi, W. Dou, J. Yu, Privacypreserving and scalable service recommendation based on simhash in a distributed cloud environment. Complexity. 2017:, 1–9 (2017). doi:10.1155/2017/3437854.
 10
F. Shi, J. Cheng, L. Wang, P. T. Yap, D. Shen, LRTV: MR image superresolution with lowrank and total variation regularizations. IEEE Trans. Med. Imaging. 34(12), 2459–2466 (2015). doi:10.1109/TMI.2015.2437894.
 11
P. Rasti, H. Demirel, G. Anbarjafari, in 2014 22nd Signal Processing and Communications Applications Conference (SIU). Improved iterative back projection for video superresolution, (2014), pp. 552–555. doi:10.1109/SIU.2014.6830288.
 12
J. Manjon, P. Coupé, A. Buades, V. Fonov, L. Collins, M. Robles, Nonlocal MRI upsampling. Med. Image Anal.14(6), 784–792 (2010). doi:10.1016/j.media.2010.05.010.
 13
Y. He, K. H. Yap, L. Chen, L. P. Chau, Blind superresolution image reconstruction using a maximum a posteriori estimation, (2006). doi:10.1109/ICIP.2006.312715.
 14
Z. Lu, C. Wu, D. Chen, Y. Qi, C. Wei, in The 26th Chinese Control and Decision Conference (2014 CCDC). Overview on image super resolution reconstruction, (2014), pp. 2009–2014. doi:10.1109/CCDC.2014.6852498.
 15
L. Y. Zhou, S. U. CaiXia, Y. F. Cao, Image superresolution via sparse representation. IEEE Trans. Image Process.19(11), 2861–2873 (2010). doi:10.1109/TIP.2010.2050625.
 16
R. Timofte, V. DeSmet, L. VanGool, in Asian Conference on Computer Vision. A+: adjusted anchored neighborhood regression for fast superresolution, (2014), pp. 111–126. doi:10.1007/9783319168173\_8.
 17
J. B. Huang, A. Singh, N. Ahuja, in 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Single image superresolution from transformed selfexemplars, (2015), pp. 5197–5206. doi:10.1109/CVPR.2015.7299156.
 18
S. Khan, M. Nawaz, G. Xu, H. Yan, Image correspondence with CUR decomposition based graph completion and matching. IEEE Trans. Circ. Syst. Video Technol.30(9), 3054–3067 (2020). doi:10.1109/TCSVT.2019.2935838.
 19
J. Zhou, X. S. Hu, Y. Ma, J. Sun, S. Hu, Improving availability of multicore realtime systems suffering both permanent and transient faults. IEEE Trans. Comput.68(12), 1785–1801 (2019). doi:10.1109/TC.2019.2935042.
 20
D. Chao, C. L. Chen, K. He, X. Tang, in European Conference on Computer Vision. Learning a deep convolutional network for image superresolution, (2014), pp. 184–199. doi:10.1007/9783319105932\_13.
 21
H. Zhu, Y. Qiao, G. Xu, L. Deng, Y. YuFeng, DSPNet: a lightweight dilated convolution neural networks for spectral deconvolution with selfpaced learning. IEEE Trans. Ind. Inform.16(12), 7392–7401 (2020). doi:10.1109/TII.2019.2960837.
 22
J. Zhou, J. Sun, X. Zhou, T. Wei, M. Chen, S. Hu, X. S. Hu, Resource management for improving softerror and lifetime reliability of realtime MPSoCs. IEEE Trans. Comput. Aided Des. Integr. Circ. Syst.38(12), 2215–2228 (2018). doi:10.1109/TCAD.2018.2883993.
 23
X. Xu, C. He, Z. Xu, L. Qi, S. Wan, M. Z. A. Bhuiyan, Joint optimization of offloading utility and privacy for edge computing enabled IoT. IEEE Internet of Things J.7(4), 2622–2629 (2019). doi:10.1109/JIOT.2019.2944007.
 24
Y. F. Yu, G. Xu, M. Jiang, H. Zhu, D. Q. Dai, H. Yan, Joint transformation learning via the L2,1norm metric for robust graph matching. IEEE Trans. Cybern., 1–13 (2019). doi:10.1109/TCYB.2019.2912718.
 25
J. Sun, Z. Xu, H. Y. Shum, Gradient profile prior and its applications in image superresolution and enhancement. IEEE Trans. Image Process.20(6), 1529–1542 (2010). doi:10.1109/TIP.2010.2095871.
 26
Y. Yu, D. Dai, C. Ren, K. Huang, Discriminative multiscale sparse coding for singlesample face recognition with occlusion. Pattern Recognit.66:, 302–312 (2017). doi:10.1016/j.patcog.2017.01.021.
 27
H. Liu, H. Kou, C. Yan, L. Qi, Link prediction in paper citation network to construct paper correlation graph. EURASIP J. Wirel. Commun. Netw.2019(1), 1–12 (2019). doi:10.1186/s1363801915617.
 28
L. Qi, X. Zhang, S. Li, S. Wan, Y. Wen, W. Gong, Spatialtemporal datadriven service recommendation with privacypreservation. Inf. Sci.515:, 91–102 (2020). doi:10.1016/j.ins.2019.11.021.
 29
L. Deng, H. Zhu, C. Tao, Y. Wei, Infrared moving point target detection based on spatialtemporal local contrast filter. Infrared Phys. Technol.76:, 168–173 (2016). doi:10.1016/j.infrared.2016.02.010.
 30
W. Zhong, X. Yin, X. Zhang, S. Li, W. Dou, R. Wang, L. Qi, Multidimensional qualitydriven service recommendation with privacypreservation in mobile edge environment. Comput. Commun.157:, 116–123 (2020). doi:10.1016/j.comcom.2020.04.018.
 31
A. Marquina, S. Osher, Image superresolution by TVregularization and Bregman iteration. J. Sci. Comput.37:, 367–382 (2008). doi:10.1007/s1091500892148.
 32
W. Zeng, X. Lu, A robust variational approach to superresolution with nonlocal TV regularisation term. Imaging Sci. J.61:, 268–278 (2013). doi:10.1179/1743131X11Y.0000000064.
 33
S. Farsiu, M. D. Robinson, M. Elad, P. Milanfar, Fast and robust multiframe super resolution. IEEE Trans. Image Process.13:, 1327–1344 (2004). doi:10.1109/TIP.2004.834669.
 34
X. Chi, C. Yan, H. Wang, W. Rafique, L. Qi, Amplified localitysensitive hashingbased recommender systems with privacy protection. Concurr. Comput. Pract. Experience, e5681 (2020). doi:10.1002/cpe.5681.
 35
X. Yuan, L. Han, S. Qian, G. Xu, H. Yan, Singular value decomposition based recommendation using imputed data. Knowl.Based Syst.163:, 485–494 (2019). doi:10.1016/j.knosys.2018.09.011.
 36
L. Qi, Q. He, F. Chen, X. Zhang, W. Dou, Q. Ni, Datadriven web APIs recommendation for building web applications. IEEE Trans. Big Data, 1–1 (2020). doi:10.1109/TBDATA.2020.2975587.
 37
A. Marquina, S. J. Osher, Image superresolution by TVregularization and Bregman iteration. J. Sci. Comput.37:, 367–382 (2008). doi:10.1007/s1091500892148.
 38
Q. Yuan, L. Zhang, H. Shen, Multiframe superresolution employing a spatially weighted total variation mode. IEEE Trans. Circ. Syst. Video Technol.22:, 379–392 (2012). doi:10.1109/TCSVT.2011.2163447.
 39
L. Li, Y. Xie, W. Hu, W. Zhang, Single image superresolution using combined total variation regularization by split Bregman Iteration. Neurocomputing. 142:, 551–560 (2014). doi:10.1016/j.neucom.2014.02.045.
 40
G. Xu, H. Zhu, L. Deng, L. Han, Y. Li, H. Lu, Dilatedaware discriminative correlation filter for visual tracking. World Wide Web. 22:, 791–805 (2019). doi:10.1007/s1128001805554.
 41
J. Lu, B. Wu, Singleimage superresolution with jointoptimization of TV regularization and sparse representation. Optik. 125:, 2497–2504 (2014). doi:10.1016/j.ijleo.2013.10.093.
 42
H. Schaeffer, Y. Yi, S. Osher, Spacetime regularization for video decompression. SIAM J. Imaging Sci.8:, 373–402 (2015). doi:10.1137/140977400.
 43
L. Qi, X. Wang, X. Xu, W. Dou, S. Li, Privacyaware crossplatform service recommendation based on enhanced localitysensitive hashing. IEEE Trans. Netw. Sci. Eng., 1–1 (2020). doi:10.1109/TNSE.2020.2969489.
 44
X. J. Chen, G. Q. Han, Z. Li, X. Liao, in 2013 International Conference on Wavelet Analysis and Pattern Recognition. Image superresolution via multiresolution image sequence, (2013), pp. 178–183. doi:10.1109/ICWAPR.2013.6599313.
 45
Y. Wang, Q. Teng, X. He, J. Feng, T. Zhang, CTimage of rock samples super resolution using 3D convolutional neural network. Comput. Geosci.133:, 104314 (2019). https://doi.org/10.1016/j.cageo.2019.104314.
 46
X. Wang, L. T. Yang, Y. Wang, L. Ren, M. J. Deen, ADTT: a highlyefficient distributed tensortrain decomposition method for IIoT big data. IEEE Trans. Ind. Inform., 1–1 (2020). doi:10.1109/TII.2020.2967768.
 47
C. Li, W. Yin, H. Jiang, Y. Zhang, An efficient augmented lagrangian method with applications to total variation minimization. Comput. Optim. Appl.53:, 507–530 (2013). doi:10.1007/s1058901395761.
 48
C. Gao, N. Wang, Q. Yu, Z. Zhang, in Aaai. A feasible nonconvex relaxation approach to feature selection, (2011), pp. 356–361. doi:10.5555/29004232900479.
 49
C. Lu, J. Tang, S. Yan, Z. Lin, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Generalized nonconvex nonsmooth lowrank minimization, (2014), pp. 4130–4137. doi:10.1109/CVPR.2014.526.
 50
H. Zhu, S. Liu, L. Deng, Y. Li, F. Xiao, Infrared small target detection via lowrank tensor completion with tophat regularization. 1004–1016. 58: (2019). doi:10.1109/TGRS.2019.2942384.
 51
G. Ongie, M. Jacob, in 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI). A fast algorithm for structured lowrank matrix recovery with applications to undersampled MRI reconstruction, (2016), pp. 522–525. doi:10.1109/ISBI.2016.7493322.
 52
H. Liu, H. Kou, C. Yan, L. Qi, Keywordsdriven and popularityaware paper recommendation based on undirected paper citation graph. Complexity. 2020(1), 1–15 (2020). doi:10.1155/2020/2085638.
 53
C. Fu, X. Ji, Y. Zhang, Q. Dai, in Data Compression Conference Proceedings. A single frame superresolution method based on matrix completion, (2012), pp. 297–306. doi:10.1109/DCC.2012.36.
 54
K. Mohan, M. Fazel, in 2010 48th Annual Allerton Conference on Communication, Control, and Computing (Allerton). Iterative reweighted least squares for matrix rank minimization, (2010), pp. 653–661. doi:10.1109/ALLERTON.2010.5706969.
Acknowledgements
Not applicable
Funding
This work is supported by the National Natural Science Foundation of China under Grant 61701259, 61572503, 61872424, 6193000388, and NUPTSF (Grant No. NY218001).
Author information
Affiliations
Contributions
The authors have contributed jointly to all parts on the preparation of this manuscript, and all authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Competing interests
The authors declare that they have no competing interests.
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
About this article
Cite this article
Deng, L., Zhou, Z., Xu, G. et al. TV2++: a novel spatialtemporal total variation for super resolution with exponentialtype norm. J Wireless Com Network 2020, 223 (2020). https://doi.org/10.1186/s13638020018150
Received:
Accepted:
Published:
Keywords
 ADMM
 ETP
 Superresolution
 TV2++