Multi-frame example-based super-resolution using locally directional self-similarity

Jeong, Seokhwa; Yoon, Inhye; Jeon, Jaehwan; Paik, Joonki

doi:10.1109/tce.2015.7298295

Cited by 19 publications

(7 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Over the past decades, a large number of image and video super-resolution approaches have been developed, ranging from traditional image processing methods such as Bilinear and Bicubic interpolation to example-based frameworks (Timofte, De, and Gool 2014;Jeong, Yoon, and Paik 2015;Xiong et al 2013;Freedman and Fattal 2011), self-similarity methods (Huang, Singh, and Ahuja 2015;Yang, Huang, and Yang 2010), and dictionary learning (Perezpellitero et al 2016). Some efforts have devoted to study different loss functions for high-quality resolution enhancement (Sajjadi, Scholkopf, and Hirsch 2017).…”

Section: Related Workmentioning

confidence: 99%

Frame and Feature-Context Video Super-Resolution

Yan

Lin

2019

AAAI

View full text Add to dashboard Cite

For video super-resolution, current state-of-the-art approaches either process multiple low-resolution (LR) frames to produce each output high-resolution (HR) frame separately in a sliding window fashion or recurrently exploit the previously estimated HR frames to super-resolve the following frame. The main weaknesses of these approaches are: 1) separately generating each output frame may obtain high-quality HR estimates while resulting in unsatisfactory flickering artifacts, and 2) combining previously generated HR frames can produce temporally consistent results in the case of short information flow, but it will cause significant jitter and jagged artifacts because the previous super-resolving errors are constantly accumulated to the subsequent frames. In this paper, we propose a fully end-to-end trainable frame and feature-context video super-resolution (FFCVSR) network that consists of two key sub-networks: local network and context network, where the first one explicitly utilizes a sequence of consecutive LR frames to generate local feature and local SR frame, and the other combines the outputs of local network and the previously estimated HR frames and features to super-resolve the subsequent frame. Our approach takes full advantage of the inter-frame information from multiple LR frames and the context information from previously predicted HR frames, producing temporally consistent highquality results while maintaining real-time speed by directly reusing previous features and frames. Extensive evaluations and comparisons demonstrate that our approach produces state-of-the-art results on a standard benchmark dataset, with advantages in terms of accuracy, efficiency, and visual quality over the existing approaches.

show abstract

Section: Related Workmentioning

confidence: 99%

Frame and Feature-Context Video Super-Resolution

Yan

Lin

2019

AAAI

View full text Add to dashboard Cite

show abstract

“…Many of these algorithms are iterative, including the Bayesian based approach [21], and the 1 -regularized total variation based approach [22]. At the same time, there are non-iterative methods that avoid registration with nonlocal mean [23], 3D steer kernel regression [24], and selfsimilarity [25]. Deep neural networks can also be used in the form of bidirectional recurrent convolutional net-works [26], and deep draft-ensemble learning [27].…”

Section: Related Work On Super Resolutionmentioning

confidence: 99%

FAST: A Framework to Accelerate Super-Resolution Processing on Compressed Videos

Zhang

Sze

2017

2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

State-of-the-art super-resolution (SR) algorithms require significant computational resources to achieve real-time throughput (e.g., 60Mpixels/s for HD video). This paper introduces FAST (Free Adaptive Super-resolution via Transfer), a framework to accelerate any SR algorithm applied to compressed videos. FAST exploits the temporal correlation between adjacent frames such that SR is only applied to a subset of frames; SR pixels are then transferred to the other frames. The transferring process has negligible computation cost as it uses information already embedded in the compressed video (e.g., motion vectors and residual). Adaptive processing is used to retain accuracy when the temporal correlation is not present (e.g., occlusions). FAST accelerates state-of-the-art SR algorithms by up to 15× with a visual quality loss of 0.2dB. FAST is an important step towards real-time SR algorithms for ultra-HD displays and energy constrained devices (e.g., phones and tablets).

show abstract

“…Jeong et al used a fuzzy system in SR image estimation. The PSF (Point Spread Function) was assumed to be a circle and for the degeneration matrix, a cyclic square matrix was employed [7]. In a study by Alqadah et al, Linear Spatial Invariant (LSI) was used to deal with PSF and Gaussian Quadratic Criterion and Lanczos algorithm was used to approximate the values of the fuzzy parameters [8].…”

Section: Introductionmentioning

confidence: 99%

Realizing the Effective Detection of Tumor in Magnetic Resonance Imaging using Cluster-Sparse Assisted Super-Resolution

Srinivasan¹,

Rajagopal²,

Velev³

et al. 2021

TOBEJ

View full text Add to dashboard Cite

Recently, significant research has been done in Super-Resolution (SR) methods for augmenting the spatial resolution of the Magnetic Resonance (MR) images, which aids the physician in improved disease diagnoses. Single SR methods have drawbacks; they fail to capture self-similarity in non-local patches and are not robust to noise. To exploit the non-local self-similarity and intrinsic sparsity in MR images, this paper proposes the use of Cluster-Sparse Assisted Super-Resolution. This SR method effectively captures similarity in non-locally positioned patches by training on clusters of patches using a self-adaptive dictionary. This method of training also leads to better edge and texture detection. Experiments show that using Cluster-Sparse Assisted Super-Resolution for brain MR images results in enhanced detection of lesions leading to better diagnosis.

show abstract

Multi-frame example-based super-resolution using locally directional self-similarity

Cited by 19 publications

References 13 publications

Frame and Feature-Context Video Super-Resolution

Frame and Feature-Context Video Super-Resolution

FAST: A Framework to Accelerate Super-Resolution Processing on Compressed Videos

Realizing the Effective Detection of Tumor in Magnetic Resonance Imaging using Cluster-Sparse Assisted Super-Resolution

Contact Info

Product

Resources

About