A Video Super-Resolution Framework Using SCoBeP

Barzigar, Nafise; Roozgard, Aminmohammad; Verma, Pramode K.; Cheng, Samuel

doi:10.1109/tcsvt.2013.2283108

Cited by 16 publications

(6 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, the image SR reconstruction with the exactly known blur and registration information, was also applied to the observed LR images to give full comparisons with the experimental results of the proposed method. The two-stage disjoint blind SR method was implemented with two steps of independent image registration procedure over the LR observed images and solving the MAP cost function in (11) with respect to the HR image and blurring function, iteratively, which is very similar to the methods in [20], except for the types of blurring function and image priors utilized to ensure the fairness of comparisons. Our proposed method was run based on the procedure shown in Fig.…”

Section: Simulated Imagesmentioning

confidence: 99%

“…Then, Kim and Su [8] extended their work by considering different blurs for each LR image. In the spatial domain, typical reconstruction methods include interpolation [9,10], iterative back projection (IBP) [11], projection onto convex sets (POCS) [12][13][14], Bayesian/maximum a posteriori (MAP) [15][16][17][18], adaptive filtering [19], and sparse coding [20].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Blind Super-Resolution Reconstruction Method Considering Image Registration Errors

Zhang

Shen

2015

Int. J. Fuzzy Syst.

View full text Add to dashboard Cite

Super-resolution (SR) image reconstruction refers to a process that produces a high-resolution (HR) image from a sequence of low-resolution images that are noisy, blurred, and downsampled. Blind SR is often necessary when the blurring function is unknown. In this paper, to reduce registration errors, we present a new joint maximum a posteriori (MAP) formulation to integrate image registration into blind image SR reconstruction. The formulation is built upon the MAP framework, which judiciously combines image registration, blur identification, and super-resolution. A cyclic coordinate descent optimization procedure is developed to solve the MAP formulation, in which the registration parameters, blurring function, and HR image are estimated in an alternative manner, given the two others, respectively. The proposed algorithm is tested using simulated as well as real-life images. The experimental results indicate that the proposed algorithm has considerable effectiveness in terms of both quantitative measurements and visual evaluation.

show abstract

Section: Simulated Imagesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Blind Super-Resolution Reconstruction Method Considering Image Registration Errors

Zhang

Shen

2015

Int. J. Fuzzy Syst.

View full text Add to dashboard Cite

show abstract

“…Before the popularization of deep learning methods, sparse coding and manual feature extraction were mainly used to deal with video super-resolution [1,2]. In reference [3], convolutional neural network is first proposed to deal with video super-resolution.…”

Section: Introductionmentioning

confidence: 99%

Video Super-Resolution Using Multi-Scale and Non-Local Feature Fusion

Zhu

Hou

et al. 2022

Electronics

View full text Add to dashboard Cite

Video super-resolution can generate corresponding to high-resolution video frames from a plurality of low-resolution video frames which have rich details and temporally consistency. Most current methods use two-level structure to reconstruct video frames by combining optical flow network and super-resolution network, but this process does not deeply mine the effective information contained in video frames. Therefore, we propose a video super-resolution method that combines non-local features and multi-scale features to extract more in-depth effective information contained in video frames. Our method obtains long-distance effective information by calculating the similarity between any two pixels in the video frame through the non-local module, extracts the local information covered by different scale convolution cores through the multi-scale feature fusion module, and fully fuses feature information using different connection modes of convolution cores. Experiments on different data sets show that the proposed method is superior to the existing methods in quality and quantity.

show abstract

“…Although a significant number of image and video SRR algorithms have already been proposed, recent advances have been mostly focused at improving the quality of the reconstructed images. This has been the case, for instance, in non-parametric spatial kernel regression methods [10], variational Bayesian methods [11], [12], non-local methods [13], [14], [15], [16], and more recently in deep-learning-based methods [17], [18], [19], [20]. Although these techniques led to considerable improvements in the quality of the reconstructed images in state-of-the-art SRR algorithms, the computational complexity associated with these strategies is very high, making them unsuitable for real-time applications.…”

Section: Introductionmentioning

confidence: 99%

Robust Online Video Super-Resolution Using an Efficient Alternating Projections Scheme

Borsoi¹

2019

Preprint

View full text Add to dashboard Cite

Video super-resolution reconstruction (SRR) algorithms attempt to reconstruct high-resolution (HR) video sequences from low-resolution (LR) observations. Although recent progress in video SRR has significantly improved the quality of the reconstructed HR sequences, it remains challenging to design SRR algorithms that achieve good quality and robustness at a small computational complexity, being thus suitable for online applications. In this paper, we propose a new adaptive video SRR algorithm that achieves state-of-the-art performance at a very small computational cost. Using a nonlinear cost function constructed considering characteristics of typical innovation outliers in natural image sequences and an edge-preserving regularization strategy, we achieve stateof-the-art reconstructed image quality and robustness. This cost function is optimized using a specific alternating projections strategy over non-convex sets that is able to converge in very few iterations. An accurate and very efficient approximation for the projection operations is also obtained using tools from multidimensional multirate signal processing. This solves the slow convergence issue of stochastic gradient-based methods while keeping a small computational complexity. Simulation results with both synthetic and real image sequences show that the performance of the proposed algorithm is similar or better than state-of-the-art SRR algorithms, while requiring only a small fraction of their computational cost.

show abstract

A Video Super-Resolution Framework Using SCoBeP

Cited by 16 publications

References 36 publications

A Blind Super-Resolution Reconstruction Method Considering Image Registration Errors

A Blind Super-Resolution Reconstruction Method Considering Image Registration Errors

Video Super-Resolution Using Multi-Scale and Non-Local Feature Fusion

Robust Online Video Super-Resolution Using an Efficient Alternating Projections Scheme

Contact Info

Product

Resources

About