Pairwise Operator Learning for Patch-Based Single-Image Super-Resolution

Tang, Yi; Shao, Ling

doi:10.1109/tip.2016.2639440

Cited by 32 publications

(8 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, some statistical properties of tensor decomposition [86] are studied, it is interesting to investigate a further understanding of both color image and multispectral image denoising with block diagonal representation. Besides, our future research also includes classification [87] and related image restoration problems [88].…”

Section: Discussionmentioning

confidence: 99%

Color Image and Multispectral Image Denoising Using Block Diagonal Representation

Kong

Yang

2019

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Filtering images of more than one channel is challenging in terms of both efficiency and effectiveness. By grouping similar patches to utilize the self-similarity and sparse linear approximation of natural images, recent nonlocal and transformdomain methods have been widely used in color and multispectral image (MSI) denoising. Many related methods focus on the modeling of group level correlation to enhance sparsity, which often resorts to a recursive strategy with a large number of similar patches. The importance of the patch level representation is understated. In this paper, we mainly investigate the influence and potential of representation at patch level by considering a general formulation with block diagonal matrix. We further show that by training a proper global patch basis, along with a local principal component analysis transform in the grouping dimension, a simple transform-threshold-inverse method could produce very competitive results. Fast implementation is also developed to reduce computational complexity. Extensive experiments on both simulated and real datasets demonstrate its robustness, effectiveness and efficiency.

show abstract

Section: Discussionmentioning

confidence: 99%

Color Image and Multispectral Image Denoising Using Block Diagonal Representation

Kong

Yang

2019

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…Other approaches do not build dictionaries out of the training data, but chose to learn simple operators, with the advantage of creating more computationally efficient solutions. Tang and Shao [36] learns two small matrices that are used on image patches as left and right multiplication operator and allow fast recovery of the high resolution image. The global nature of these matrices, however, fails to capture small details and complex textures.…”

Section: A Approaches Using External Datamentioning

confidence: 99%

Single Image Super-Resolution Based on Wiener Filter in Similarity Domain

Cruz

Mehta

Katkovnik

et al. 2018

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Single image super-resolution (SISR) is an ill-posed problem aiming at estimating a plausible high-resolution (HR) image from a single low-resolution image. Current state-of-the-art SISR methods are patch-based. They use either external data or internal self-similarity to learn a prior for an HR image. External data-based methods utilize a large number of patches from the training data, while self-similarity-based approaches leverage one or more similar patches from the input image. In this paper, we propose a self-similarity-based approach that is able to use large groups of similar patches extracted from the input image to solve the SISR problem. We introduce a novel prior leading to the collaborative filtering of patch groups in a 1D similarity domain and couple it with an iterative back-projection framework. The performance of the proposed algorithm is evaluated on a number of SISR benchmark data sets. Without using any external data, the proposed approach outperforms the current non-convolutional neural network-based methods on the tested data sets for various scaling factors. On certain data sets, the gain is over 1 dB, when compared with the recent method A+. For high sampling rate (x4), the proposed method performs similarly to very recent state-of-the-art deep convolutional network-based approaches.

show abstract

“…A+ studies the mapping relationship between the LR and HR samples in a much denser sample space, which can guarantee the performance of local linear regression. In addition to the work of [37]- [39], some regression algorithms also have been developed to directly learn the relationship between the LR samples and HR samples in a coarse-to-fine [40], [41], sparse [42]- [44], collaborative [45], [46], adaptive [9], local [47], [48], pairwise [49] or structured [50] manner. The above mentioned algorithms are simple, fast, and can well characterize the potential mapping between the LR and HR spaces (especially the local image patch space), and thus they produced very favorable performance.…”

Section: Introductionmentioning

confidence: 99%

Ensemble Super-Resolution With a Reference Dataset

Jiang

Wang

et al. 2020

IEEE Trans. Cybern.

View full text Add to dashboard Cite

By developing sophisticated image priors or designing deep(er) architectures, a variety of image Super-Resolution (SR) approaches have been proposed recently and achieved very promising performance. A natural question that arises is whether these methods can be reformulated into a unifying framework and whether this framework assists in SR reconstruction? In this paper, we present a simple but effective single image SR method based on ensemble learning, which can produce a better performance than that could be obtained from any of SR methods to be ensembled (or called component superresolvers). Based on the assumption that better component superresolver should have larger ensemble weight when performing SR reconstruction, we present a Maximum A Posteriori (MAP) estimation framework for the inference of optimal ensemble weights. Specially, we introduce a reference dataset, which is composed of High-Resolution (HR) and Low-Resolution (LR) image pairs, to measure the super-resolution abilities (prior knowledge) of different component super-resolvers. To obtain the optimal ensemble weights, we propose to incorporate the reconstruction constraint, which states that the degenerated HR image should be equal to the LR observation one, as well as the prior knowledge of ensemble weights into the MAP estimation framework. Moreover, the proposed optimization problem can be solved by an analytical solution. We study the performance of the proposed method by comparing with different competitive approaches, including four state-of-the-art non-deep learning based methods, four latest deep learning based methods and one ensemble learning based method, and prove its effectiveness and superiority on three public datasets.

show abstract

Pairwise Operator Learning for Patch-Based Single-Image Super-Resolution

Cited by 32 publications

References 43 publications

Color Image and Multispectral Image Denoising Using Block Diagonal Representation

Color Image and Multispectral Image Denoising Using Block Diagonal Representation

Single Image Super-Resolution Based on Wiener Filter in Similarity Domain

Ensemble Super-Resolution With a Reference Dataset

Contact Info

Product

Resources

About