A reduced-reference quality assessment metric for super-resolution reconstructed images with information gain and texture similarity

Tang, Lijuan; Sun, Kewen; Liu, Luping; Wang, Guangcheng; Liu, Yutao

doi:10.1016/j.image.2019.08.004

Cited by 21 publications

(8 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a few papers, the authors proposed reducedreference metrics, which use low-resolution (LR) images as a reference. A popular approach is to extract structure or texture features from LR and upscaled (SR) images, compare them separately, and fuse the resulting similarity indices (Yeganeh et al, 2015;Tang et al, 2019;Fang et al, 2019). Metrics based on this idea achieve a Pearson correlation coefficient of 0.79 to 0.83 and a Spearman correlation coefficient of 0.69 to 0.85 on various datasets, depending on the implementation.…”

Section: Related Workmentioning

confidence: 99%

ERQA: Edge-Restoration Quality Assessment for Video Super-Resolution

Kirillova¹,

Eugene²,

Antsiferova³

et al. 2021

Preprint

View full text Add to dashboard Cite

Despite the growing popularity of video super-resolution (VSR), there is still no good way to assess the quality of the restored details in upscaled frames. Some SR methods may produce the wrong digit or an entirely different face. Whether a method's results are trustworthy depends on how well it restores truthful details. Image super-resolution can use natural distributions to produce a high-resolution image that is only somewhat similar to the real one. VSR enables exploration of additional information in neighboring frames to restore details from the original scene. The ERQA metric, which we propose in this paper, aims to estimate a model's ability to restore real details using VSR. On the assumption that edges are significant for detail and character recognition, we chose edge fidelity as the foundation for this metric. Experimental validation of our work is based on the MSU Video Super-Resolution Benchmark, which includes the most difficult patterns for detail restoration and verifies the fidelity of details from the original frame. Code for the proposed metric is publicly available at https://github.com/msu-video-group/ERQA. a https://orcid.

show abstract

Section: Related Workmentioning

confidence: 99%

ERQA: Edge-Restoration Quality Assessment for Video Super-Resolution

Kirillova¹,

Eugene²,

Antsiferova³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Fang et al introduced a reduced-reference quality assessment method for image SR by predicting the energy and texture similarity between LR and HR images [16]. In [10], Tang et al proposed another reduced-reference IQA algorithm for SR reconstructed images with information gain and texture similarity combining saliency detection. Ma et al proposed a no-reference metric by supervised learning on a large set of reference-free HR images [9].…”

Section: Related Workmentioning

confidence: 99%

“…The source codes of these metrics are obtained from the authors' public websites. There are two other SR-IQA metrics [10], [16] without publicly available codes and parameters, thus they are not compared in the table. From Table V, we have the following observations: First, FocusLiteNN obtains the highest PLCC on the Waterloo-15 database, and the HOSA achieves the best performance on SRCC and KRCC.…”

Section: B Performance Comparisonmentioning

confidence: 99%

“…In a typical image SR problem, the perfect quality HR image is unavailable as a reference, therefore, full-reference models are generally inapplicable. In addition, SR algorithms often introduce mixed impairments, including blurring, ringing and aliasing artifacts, which are not well measured by the existing methods [9], [10]. Therefore, conventional general-purpose reduced-reference and noreference IQA models should be redesigned specifically for image SR problem.…”

Section: Introductionmentioning

confidence: 99%

“…Compared with other data-driven models, CNN is capable of learning features and making quality predictors jointly in an end-to-end manner. Despite its superiority, CNN has not yet been well exploited in SR-IQA, for which most methods are not based on deep learning [9], [10], [14]- [16]. In this work, we propose a CNN-based SR-IQA algorithm.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Learning-Based Quality Assessment for Image Super-Resolution

Zhao¹,

Lin²,

Xu³

et al. 2020

Preprint

View full text Add to dashboard Cite

Image Super-Resolution (SR) techniques improve visual quality by enhancing the spatial resolution of images. Quality evaluation metrics play a critical role in comparing and optimizing SR algorithms, but current metrics achieve only limited success, largely due to the lack of large-scale quality databases, which are essential for learning accurate and robust SR quality metrics. In this work, we first build a largescale SR image database using a novel semi-automatic labeling approach, which allows us to label a large number of images with manageable human workload. The resulting SR Image quality database with Semi-Automatic Ratings (SISAR), so far the largest of SR-IQA database, contains 8,400 images of 100 natural scenes. We train an end-to-end Deep Image SR Quality (DISQ) model by employing two-stream Deep Neural Networks (DNNs) for feature extraction, followed by a feature fusion network for quality prediction. Experimental results demonstrate that the proposed method outperforms state-of-the-art metrics and achieves promising generalization performance in crossdatabase tests. The SISAR database and DISQ model will be made publicly available to facilitate reproducible research.

show abstract

Optical flow for video super-resolution: a survey

Xie

et al. 2022

Artif Intell Rev

View full text Add to dashboard Cite

A reduced-reference quality assessment metric for super-resolution reconstructed images with information gain and texture similarity

Cited by 21 publications

References 30 publications

ERQA: Edge-Restoration Quality Assessment for Video Super-Resolution

ERQA: Edge-Restoration Quality Assessment for Video Super-Resolution

Learning-Based Quality Assessment for Image Super-Resolution

Optical flow for video super-resolution: a survey

Contact Info

Product

Resources

About