Image super-resolution via two coupled dictionaries and sparse representation

Alvarez-Ramos, Valentin; Ponomaryov, Volodymyr; Reyes-Reyes, Rogelio

doi:10.1007/s11042-017-4968-3

Cited by 8 publications

(2 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, nearest-neighbor patch method enlarged the influences of local pixel points via relation of different areas from the given LR image to achieve the high-resolution image [7]. In terms of improving the efficiency, sparse representation technique was also a good choice in SISR [8,10]. For instance, the combination of discrete wavelet transform, principal components analysis and sparse representation can reduce the information dimension to obtain more better expression carrier of the goal task for SISR [9].…”

Section: Introductionmentioning

confidence: 99%

Asymmetric CNN for image super-resolution

Tian¹,

Xu²,

Zuo³

et al. 2021

Preprint

View full text Add to dashboard Cite

Deep convolutional neural networks (CNNs) have been widely applied for low-level vision over the past five years. According to nature of different applications, designing appropriate CNN architectures is developed. However, customized architectures gather different features via treating all pixel points as equal to improve the performance of given application, which ignores the effects of local power pixel points and results in low training efficiency. In this paper, we propose an asymmetric CNN (ACNet) comprising an asymmetric block (AB), a memory enhancement block (MEB) and a high-frequency feature enhancement block (HFFEB) for image super-resolution. The AB utilizes one-dimensional asymmetric convolutions to intensify the square convolution kernels in horizontal and vertical directions for promoting the influences of local salient features for SISR. The MEB fuses all hierarchical low-frequency features from the AB via residual learning (RL) technique to resolve the long-term dependency problem and transforms obtained low-frequency features into high-frequency features. The HFFEB exploits low-and high-frequency features to obtain more robust super-resolution features and address excessive feature enhancement problem. Additionally, it also takes charge of reconstructing a high-resolution (HR) image. Extensive experiments show that our ACNet can effectively address single image super-resolution (SISR), blind SISR and blind SISR of blind noise problems. The code of the ACNet is shown at https://github.com/hellloxiaotian/ACNet.

show abstract

Section: Introductionmentioning

confidence: 99%

Asymmetric CNN for image super-resolution

Tian¹,

Xu²,

Zuo³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Since Yang et al. first applied sparse representation to super-resolution reconstruction [27,28], many scholars have proposed improved methods for super-resolution reconstruction based on sparse representation [29,30,31,32,33,34,35]. In recent years, Selesnick and Chen proposed overlapping group sparse total variation (OGSTV) [36], which is a non-separating regular term that preserves the sparsity of the objective function [37].…”

Section: Introductionmentioning

confidence: 99%

Infrared Image Super-Resolution Reconstruction Based on Quaternion and High-Order Overlapping Group Sparse Total Variation

Liu

Chen

Peng

et al. 2019

Sensors

View full text Add to dashboard Cite

Owing to the limitations of imaging principles and system imaging characteristics, infrared images generally have some shortcomings, such as low resolution, insufficient details, and blurred edges. Therefore, it is of practical significance to improve the quality of infrared images. To make full use of the information on adjacent points, preserve the image structure, and avoid staircase artifacts, this paper proposes a super-resolution reconstruction method for infrared images based on quaternion total variation and high-order overlapping group sparse. The method uses a quaternion total variation method to utilize the correlation between adjacent points to improve image anti-noise ability and reconstruction effect. It uses the sparsity of a higher-order gradient to reconstruct a clear image structure and restore smooth changes. In addition, we performed regularization by using the denoising method, alternating direction method of multipliers, and fast Fourier transform theory to improve the efficiency and robustness of our method. Our experimental results show that this method has excellent performance in objective evaluation and subjective visual effects.

show abstract

Toward Understanding the Impact of Input Data for Multi-Image Super-Resolution

Adler

Kawulok

2022

Intelligent Information and Database Systems

View full text Add to dashboard Cite

Image super-resolution via two coupled dictionaries and sparse representation

Cited by 8 publications

References 42 publications

Asymmetric CNN for image super-resolution

Asymmetric CNN for image super-resolution

Infrared Image Super-Resolution Reconstruction Based on Quaternion and High-Order Overlapping Group Sparse Total Variation

Toward Understanding the Impact of Input Data for Multi-Image Super-Resolution

Contact Info

Product

Resources

About