Learning Blind Quality Evaluator for Stereoscopic Images Using Joint Sparse Representation

Shao, Feng; Li, Kemeng; Wang, Lin; Jiang, Gangyi; Dai, Qionghai

doi:10.1109/tmm.2016.2594142

Cited by 44 publications

(24 citation statements)

References 70 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhou et al [75] first presented two binocular combinations of stimuli, generated by an eye-weighting model and a contrast-gain control model, and then used the ELM to perform a fidelity prediction. Shao et al [76] presented a framework for NR 3D image fidelity assessment by combining feature-prior and feature-distribution, which characterizes feature-prior by SVR and implements feature-distribution by sparsity regularization as the basis of weights for binocular combination. Shao et al [77] proposed a domain transfer framework for NR fidelity prediction of asymmetrically distorted 3D images.…”

Section: ) No-reference 3d Image Fidelity Assessmentmentioning

confidence: 99%

“…So the experimented metrics usually perform better on the LIVE 3D IQA database Phase-I and NBU 3D IQA database than on the LIVE 3D IQA database Phase-II. In recent years, machine learning and deep learning based metrics [71], [75], [76], [80], [81] have achieved significant performance improvements, especially for asymmetrically distorted images. The performance of state-or-the-art NR metrics [76], [80]- [82] is similar to that of state-or-the-art FR metrics [71], [72].…”

Section: ) Live 3d Iqa Database Phase-i [125]mentioning

confidence: 99%

See 1 more Smart Citation

2D and 3D Image Quality Assessment: A Survey of Metrics and Challenges

et al. 2019

View full text Add to dashboard Cite

Image quality is important not only for the viewing experience, but also for the performance of image processing algorithms. Image quality assessment (IQA) has been a topic of intense research in the fields of image processing and computer vision. In this paper, we first analyze the factors that affect twodimensional (2D) and three-dimensional (3D) image quality, and then provide an up-to-date overview on IQA for each main factor. The main factors that affect 2D image quality are fidelity and aesthetics. Another main factor that affects stereoscopic 3D image quality is visual comfort. We also describe the IQA databases and give the experimental results on representative IQA metrics. Finally, we discuss the challenges for IQA, including the influence of different factors on each other, the performance of IQA metrics in real applications, and the combination of quality assessment, restoration, and enhancement. INDEX TERMS Image quality assessment, image aesthetics assessment, visual comfort, and image quality enhancement.

show abstract

Section: ) No-reference 3d Image Fidelity Assessmentmentioning

confidence: 99%

Section: ) Live 3d Iqa Database Phase-i [125]mentioning

confidence: 99%

2D and 3D Image Quality Assessment: A Survey of Metrics and Challenges

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Various stereoscopic image quality assessment algorithms have been proposed in literature [21][22][23][24][25][26], however the quality assessment of DIBR-synthesized images is relatively less investigated. To quantify the structural distortion in synthesized view due to DIBR, Bosc et al [27] compared the edges of the original and the warped images.…”

Section: Related Workmentioning

confidence: 99%

Evaluating virtual image quality using the side-views information fusion and depth maps

2018

View full text Add to dashboard Cite

Three Dimensional (3D) image quality assessment is a challenging problem as compared to 2D images due to their different nature of acquisition, representation, coding, and display. The additional dimension of depth in multiview video plus depth (MVD) format is exploited to obtain images at novel intermediate viewpoints using depth image based rendering (DIBR) techniques, enabling 3D television and free-viewpoint television (FTV) applications. Depth maps introduce various quality artifacts in the DIBR-synthesized (virtual) images. In this paper, we propose a novel methodology to evaluate the quality of synthesized views in absence of the corresponding original reference views. It computes the statistical characteristics of the side views from whom the virtual view is generated, and fuses this information to estimate the statistical characteristics of the cyclopean image which are compared to those of the synthesized image to evaluate its quality. In addition to texture images, the proposed algorithm also considers the depth maps in evaluating the quality of the synthesized images. The algorithm blends two quality metrics, one estimating the texture distortion in the synthesized texture image induced by compression, transmission, 3D warping, or other causes and the second one determining the distortion of the depth maps. The two metrics are combined to obtain an overall quality assessment of the synthesized image. The proposed Synthesized Image Quality Metric (SIQM) is tested on the challenging MCL-3D and SIAT-3D datasets. The evaluation results show that the proposed metric significantly improves over state-of-the-art 3D image quality assessment algorithms.

show abstract

“…To cope with this challenge, many works have been proposed. Shao et al [16] proposed a blind SIQA method using joint sparse representation, in which stereoscopic image quality is predicted based on the weighted monocular quality score. To handle the asymmetric distortion, Shao et al [17] designed an NR metric by utilizing both monocular and binocular properties for quality assessment.…”

Section: Introductionmentioning

confidence: 99%

Blind Stereoscopic Image Quality Assessment Accounting for Human Monocular Visual Properties and Binocular Interactions

et al. 2020

View full text Add to dashboard Cite

Human visual perceptual model is a key factor for evaluating stereoscopic image quality. This paper focuses on the contributions of monocular and binocular properties on quality perception and proposes a novel blind stereoscopic image quality assessment model by comprehensively digging the relationship between visual features and quality perception. The statistical quality-aware monocular features are extracted from both left view and right view to reveal monocular quality perception, including the color statistical features which are missed in most previous models, while the multiple features of the summation signal and the entropy features of the difference signal are extracted to quantify the binocular quality perception. Finally, support vector regression (SVR) is utilized to train a regression model based on the extracted features and the subjective scores. Three public databases, LIVE 3D Phase I, LIVE 3D Phase II, and MCL 3D Database, are adopted to prove the effectiveness of the proposed model. Experimental results demonstrate that the proposed model is superior to other existing state-of-the-art quality metrics. INDEX TERMS Stereoscopic image quality, monocular feature, binocular feature, human visual system.

show abstract

Learning Blind Quality Evaluator for Stereoscopic Images Using Joint Sparse Representation

Cited by 44 publications

References 70 publications

2D and 3D Image Quality Assessment: A Survey of Metrics and Challenges

2D and 3D Image Quality Assessment: A Survey of Metrics and Challenges

Evaluating virtual image quality using the side-views information fusion and depth maps

Blind Stereoscopic Image Quality Assessment Accounting for Human Monocular Visual Properties and Binocular Interactions

Contact Info

Product

Resources

About