Semi-Coupled Convolutional Sparse Learning for Image Super-Resolution

Zhang, Sibo; Jiao, Licheng; Liu, Fang; Yang, Shuyuan; Tang, Xu

doi:10.3390/rs11212593

Cited by 3 publications

(2 citation statements)

References 56 publications

(78 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Single image super-resolution (SR), aims at recovering a high-resolution image (HR) from its low-resolution image (LR) counterpart [ 1 ]. There is a recognized need for SR techniques in many fields [ 2 , 3 , 4 , 5 , 6 , 7 ], such as remote sensing, medical imaging, security surveillance, and hyperspectral images to name a few.…”

Section: Introductionmentioning

confidence: 99%

Lightweight Single Image Super-Resolution with Selective Channel Processing Network

Zhu

Tang

et al. 2022

Sensors

View full text Add to dashboard Cite

With the development of deep learning, considerable progress has been made in image restoration. Notably, many state-of-the-art single image super-resolution (SR) methods have been proposed. However, most of them contain many parameters, which leads to a significant amount of calculation consumption in the inference phase. To make current SR networks more lightweight and resource-friendly, we present a convolution neural network with the proposed selective channel processing strategy (SCPN). Specifically, the selective channel processing module (SCPM) is first designed to dynamically learn the significance of each channel in the feature map using a channel selection matrix in the training phase. Correspondingly, in the inference phase, only the essential channels indicated by the channel selection matrixes need to be further processed. By doing so, we can significantly reduce the parameters and the calculation consumption. Moreover, the differential channel attention (DCA) block is proposed, which takes into consideration the data distribution of the channels in feature maps to restore more high-frequency information. Extensive experiments are performed on the natural image super-resolution benchmarks (i.e., Set5, Set14, B100, Urban100, Manga109) and remote-sensing benchmarks (i.e., UCTest and RESISCTest), and our method achieves superior results to other state-of-the-art methods. Furthermore, our method keeps a slim size with fewer than 1 M parameters, which proves the superiority of our method. Owing to the proposed SCPM and DCA, our SCPN model achieves a better trade-off between calculation cost and performance in both general and remote-sensing SR applications, and our proposed method can be extended to other computer vision tasks for further research.

show abstract

Section: Introductionmentioning

confidence: 99%

Lightweight Single Image Super-Resolution with Selective Channel Processing Network

Zhu

Tang

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…To use the consistency prior, an SR reconstruction scheme based on convolutional sparse coding (CSC-SR) was T proposed in [19], which takes the entire image as an input and uses convolution filters and feature maps to estimate the target image. Nonlinear convolution operations were used as the mapping function between LR and HR features in a semicoupled convolutional sparse learning method (SCCSL) [20], which reduce the coupling between LR and HR representations. Using the adaptive CSC and CNN to reconstruct the texture part and the smooth part of the input image, respectively, a hybrid adaptive convolutional sparse coding-based super-resolution (HACSC-SR) method was proposed [21].…”

mentioning

confidence: 99%

Single Satellite Imagery Superresolution Based on Hybrid Nonlocal Similarity Constrained Convolution Sparse Coding

Chen

Sui

Zhang³

et al. 2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

The traditional super-resolution methods based on image patches often ignore the consistency between the overlapped patches, causing block effects in produced images. The convolutional sparse coding based super-resolution method uses the translation invariance of the convolution filter to directly encode the entire image, maintaining consistency and good performance. In this paper, we propose a novel approach to single image super-resolution reconstruction based on hybrid nonlocal similarity constrained convolution sparse coding. We first decompose the input image into a smooth part and a texture part. The Bayesian nonparametric model can use more prior information of the original image, so we replace the previous bicubic interpolation with this method to better reconstruct the residual high-frequency information in the smooth part. When reconstructing the texture part, this paper proposes a nonlocal similarity constrained convolutional sparse coding method, which transforms the reconstruction of the texture part to minimize the convolution sparse coding noise of the feature maps and classifies the image patches in the search space by using the correlation coefficients as the structural information, avoiding unnecessary weight calculation. Several methods were tested on satellite images extensively. Both visual inspection and quantitative analysis results demonstrate that our method outperforms other state-of-the-art methods and increases noise immunity effectively.

show abstract

Multi-Scale Semi-Coupled Convolutional Sparse Coding for the Super-Resolution Reconstruction of Remote Sensing Image

Chen¹,

Zhang²

2022

J Comput-Aided Design Comput Graphics

View full text Add to dashboard Cite

Semi-Coupled Convolutional Sparse Learning for Image Super-Resolution

Cited by 3 publications

References 56 publications

Lightweight Single Image Super-Resolution with Selective Channel Processing Network

Lightweight Single Image Super-Resolution with Selective Channel Processing Network

Single Satellite Imagery Superresolution Based on Hybrid Nonlocal Similarity Constrained Convolution Sparse Coding

Multi-Scale Semi-Coupled Convolutional Sparse Coding for the Super-Resolution Reconstruction of Remote Sensing Image

Contact Info

Product

Resources

About