Consistent Coding Scheme for Single-Image Super-Resolution Via Independent Dictionaries

Yang, Wenming; Tian, Yapeng; Zhou, Fei; Liao, Qingmin; Hai, Chen; Zheng, Cao

doi:10.1109/tmm.2016.2515997

Cited by 56 publications

(19 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Citation information: DOI 10.1109/TIP.2019.2898638, IEEE Transactions on Image Processing 2 can be represented sparsely using a specified dictionary. It has many extensions, such as adaptive sparse domain selection (ASDS) [18], semi-coupled dictionary learning (SCDL) [19], statistical prediction model (SPM) [20], compact kernel sub-dictionary learning [21], consistent coding scheme (CCS) [22], etc. These extensions have achieved success via the incorporation of more knowledge in the image priors.…”

Section: A Image Super-resolutionmentioning

confidence: 99%

Visual Quality Assessment for Super-Resolved Images: Database and Method

Zhou

Yao

Liu

et al. 2019

IEEE Trans. on Image Process.

Self Cite

View full text Add to dashboard Cite

Image super-resolution (SR) has been an active research problem which has recently received renewed interest due to the introduction of new technologies such as deep learning. However, the lack of suitable criteria to evaluate the SR performance has hindered technology development. In this paper, we fill a gap in the literature by providing the first publicly available database as well as a new image quality assessment (IQA) method specifically designed for assessing the visual quality of super-resolved images (SRIs). In constructing the Quality Assessment Database for SRIs (QADS), we carefully selected 20 reference images and created 980 SRIs using 21 image SR methods. Mean opinion score (MOS) for these SRIs are collected through 100 individuals participating a suitably designed psychovisual experiment. Extensive numerical and statistical analysis is performed to show that the MOS of QADS has excellent suitability and reliability. The psychovisual experiment has led to the discovery that, unlike distortions encountered in other IQA databases, artifacts of the SRIs degenerate the image structure as well as image texture. Moreover, the structural and textural degenerations have distinctive perceptual properties. Based on these insights, we propose a novel method to assess the visual quality of SRIs by separately considering the structural and textural components of images. Observing that textural degenerations are mainly attributed to dissimilar texture or checkerboard artifacts, we propose to measure the changes of textural distributions. We also observe that structural degenerations appear as blurring and jaggies artifacts in SRIs and develop separate similarity measures for different types of structural degenerations. A new pooling mechanism is then used to fuse the different similarities together to give the final quality score for an SRI. Experiments conducted on the QADS demonstrate that our method significantly outperforms classical as well as current state-of-the-art IQA methods.

show abstract

Section: A Image Super-resolutionmentioning

confidence: 99%

Visual Quality Assessment for Super-Resolved Images: Database and Method

Zhou

Yao

Liu

et al. 2019

IEEE Trans. on Image Process.

Self Cite

View full text Add to dashboard Cite

show abstract

“…I MAGE quality assessment (IQA) is widely used as a benchmark in numerous image processing tasks, such as image super-resolution [1], image compression [2], and image enhancement [3]. Subjective assessment by humans is the most accurate IQA metric because images are finally presented to human beings.…”

mentioning

confidence: 99%

SPSIM: A Superpixel-Based Similarity Index for Full-Reference Image Quality Assessment

Sun

Liao

Xue

et al. 2018

IEEE Trans. on Image Process.

Self Cite

View full text Add to dashboard Cite

Full-reference image quality assessment algorithms usually perform comparisons of features extracted from square patches. These patches do not have any visual meanings. On the contrary, a superpixel is a set of image pixels that share similar visual characteristics and is thus perceptually meaningful. Features from superpixels may improve the performance of image quality assessment. Inspired by this, we propose a new superpixel-based similarity index by extracting perceptually meaningful features and revising similarity measures. The proposed method evaluates image quality on the basis of three measurements, namely, superpixel luminance similarity, superpixel chrominance similarity, and pixel gradient similarity. The first two measurements assess the overall visual impression on local images. The third measurement quantifies structural variations. The impact of superpixel-based regional gradient consistency on image quality is also analyzed. Distorted images showing high regional gradient consistency with the corresponding reference images are visually appreciated. Therefore, the three measurements are further revised by incorporating the regional gradient consistency into their computations. A weighting function that indicates superpixel-based texture complexity is utilized in the pooling stage to obtain the final quality score. Experiments on several benchmark databases demonstrate that the proposed method is competitive with the state-of-the-art metrics.

show abstract

“…It is a notoriously challenging problem since a specific LR input corresponds to a crop of possible HR images and no unique solution exists. To tackle this ill-posed problem, many learning methods have been proposed, such as neighbor embedding methods [1], [2], sparse coding methods [3], [4], [5] and random forest methods [6]. Since Dong et al firstly introduce a Super-Resolution Convolutional Neural Network (SRCNN) [7] to learn a nonlinear LR to HR mapping function, convolutional neural networks (CNNs) based SR has demonstrated outperformance over the traditional methods.…”

Section: Introductionmentioning

confidence: 99%

Lightweight Super-Resolution Using Deep Neural Learning

Jiang

Zhu

et al. 2020

IEEE Trans. on Broadcast.

View full text Add to dashboard Cite

There is a gap between recent development of 4K display technologies and the short storage of 4K contents. Super-Resolution (SR) serves as a bridge to harmonize the need and demand. Recently, Convolutional Neural Network (CNN) based networks have demonstrated great property in image SR. However, most existing methods require large model capacity and consume expensive computation for high performance. Besides, most methods keep the upscaling part relatively simple compared with the feature extraction part. For feature fusion, some methods directly concatenate the features of multilevels, which is suboptimal due to ignoring the importance of different features. In this work, we propose a recursive multi-stage upscaling network (RMUN) with multiple subupscaling modules (SUMs) and a discriminative self-ensemble module (SEM). Specifically, we extract local hierarchical features by using a novel feature extraction module (FEM) which is recursive to reduce the number of parameters. Then, we construct multiple sub-upscaling modules to produce various high-resolution features in forward propagation. This strategy enhances the upscaling part and provides multiple error feedback routes. Furthermore, we employ an SEM for global hierarchical feature recalibration, which can selectively emphasize informative features and surpass less useful ones. Extensive quantitative and qualitative evaluations on benchmark datasets show that our proposed method performs comparable with the state-ofthe-art methods in terms of the balance of model size and model performance.

show abstract

Consistent Coding Scheme for Single-Image Super-Resolution Via Independent Dictionaries

Cited by 56 publications

References 29 publications

Visual Quality Assessment for Super-Resolved Images: Database and Method

Visual Quality Assessment for Super-Resolved Images: Database and Method

SPSIM: A Superpixel-Based Similarity Index for Full-Reference Image Quality Assessment

Lightweight Super-Resolution Using Deep Neural Learning

Contact Info

Product

Resources

About