Single image super-resolution via adaptive sparse representation and low-rank constraint

Li, Xuesong; Cao, Guo; Zhang, Youqiang; Wang, Bisheng

doi:10.1016/j.jvcir.2018.06.012

Cited by 12 publications

(12 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this subsection, our method is compared with Bicubic interpolation, ScSR [13], ANR [17], ASCSR [33], SRCNN [26], ASR+LR [34], and the experimental results on ten images shown in Fig. 1 are presented.…”

Section: Effectiveness Of Our Proposed Methodsmentioning

confidence: 99%

“…To sum up, our jobs not only have higher performance to reveal the details of the image but also have better actual SR reconstruction effect. [13], ANR [17], ASCSR [33], SRCNN [26]，ASR+LR [34],…”

Section: Effectiveness Of Our Proposed Methodsmentioning

confidence: 99%

“…Comparison of our method with Bicubic, ScSR [13], ANR [17], ASCSR [33], SRCNN [26] and ASR+LR [34](scaling factor 2 s = ). [13], ANR [17], ASCSR [33], SRCNN [26], ASR+LR [34], Proposed method. [13], ANR [17], ASCSR [33], SRCNN [26],ASR+LR [34], Proposed method.…”

Section: Effectiveness Of Our Proposed Methodsmentioning

confidence: 99%

“…Recently, many researchers have shown great interest in the low-rank representation (LRR) and apply it into image SR reconstruction [3], [32][33][34][35][36][37][38][39], data clustering [40][41][42], and other fields. In [32], Chen et al introduce the low-rank matrix recovery (LRMR) technique into the neighbor embedding (NE) SR method and obtain excellent results.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Low-Rank Representation-Based Image Super-Resolution Reconstruction with Edge-Preserving

2020

KSII TIIS

View full text Add to dashboard Cite

Low-rank representation methods already achieve many applications in the image reconstruction. However, for high-gradient image patches with rich texture details and strong edge information, it is difficult to find sufficient similar patches. Existing low-rank representation methods usually destroy image critical details and fail to preserve edge structure. In order to promote the performance, a new representation-based image super-resolution reconstruction method is proposed, which combines gradient domain guided image filter with the structure-constrained low-rank representation so as to enhance image details as well as reveal the intrinsic structure of an input image. Firstly, we extract the gradient domain guided filter of each atom in high resolution dictionary in order to acquire high-frequency prior information. Secondly, this prior information is taken as a structure constraint and introduced into the low-rank representation framework to develop a new model so as to maintain the edges of reconstructed image. Thirdly, the approximate optimal solution of the model is solved through alternating direction method of multipliers. After that, experiments are performed and results show that the proposed algorithm has higher performances than conventional state-of-the-art algorithms in both quantitative and qualitative aspects.

show abstract

Section: Effectiveness Of Our Proposed Methodsmentioning

confidence: 99%

Section: Effectiveness Of Our Proposed Methodsmentioning

confidence: 99%

Section: Effectiveness Of Our Proposed Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Low-Rank Representation-Based Image Super-Resolution Reconstruction with Edge-Preserving

2020

KSII TIIS

View full text Add to dashboard Cite

show abstract

“…Therefore, a more reasonable choice is to take the sparsity and correlation simultaneously into consideration. Inspired by the trace lasso [53,54], we propose a novel spatial-spectral adaptive non-negative sparse representation (ANSR) method for HSI super-resolution by fusing the LR-HSI and corresponding HR-MSI. The proposed method integrates sparsity and correlation effectively as a regularization term in the model and can produce more suitable coefficients adaptively with the constraint between 1 -norm and 2 -norm.…”

mentioning

confidence: 99%

Adaptive Nonnegative Sparse Representation for Hyperspectral Image Super-Resolution

Zhang

et al. 2021

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

Self Cite

View full text Add to dashboard Cite

As the Hyperspectral (HS) images usually have low spatial resolution, hyperspectral image (HSI) super-resolution has recently attracted more and more attention to enhance the spatial resolution of HSIs. A common method is to fuse the low-resolution (LR) HSI with a multispectral image (MSI) whose spatial resolution is higher than the HSI. In this paper, we proposed a novel adaptive non-negative sparse representation (ANSR) based model to fuse an HSI and its corresponding MSI. First, basing the linear spectral unmixing, the non-negative structured sparse representation model estimates the sparse codes of the desired high-resolution (HR) HSI from both the LR-HSI and the MSI. Then, the adaptive sparse representation (ASR) can balance the relationship between the sparsity and collaboration by generating a suitable coefficient. Finally, in order to obtain more accurate results, we alternately optimize the spectral basis and coefficients rather than keeping the spectral basis fixed. Alternating direction method of multipliers is applied to solve the proposed optimization problem. Experimental results on both ground-based hyperspectral images and real remote sensing HSIs show the superiority of our proposed approach to some other state-of-the-art HSI super-resolution methods.

show abstract

Classification of priors and regularization techniques appurtenant to single image super-resolution

Pandey

Ghanekar

2019

Vis Comput

View full text Add to dashboard Cite

Single image super-resolution via adaptive sparse representation and low-rank constraint

Cited by 12 publications

References 59 publications

Low-Rank Representation-Based Image Super-Resolution Reconstruction with Edge-Preserving

Low-Rank Representation-Based Image Super-Resolution Reconstruction with Edge-Preserving

Adaptive Nonnegative Sparse Representation for Hyperspectral Image Super-Resolution

Classification of priors and regularization techniques appurtenant to single image super-resolution

Contact Info

Product

Resources

About