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

Niu, Yuzhen; Zhong, Yini; Guo, Wenzhong; Shi, Yiqing; Chen, Peikun

doi:10.1109/access.2018.2885818

Cited by 48 publications

(33 citation statements)

References 126 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The computational complexity of these methods was determined in terms of their execution time. In a recent survey [34], different areas of IQA are reviewed including two-dimensional (2D) image fidelity assessment (FR, RR, NR), three-dimensional (3D) image fidelity assessment (FR, NR), image aesthetics assessment, and 3D image visual comfort assessment. In the category of 2D image fidelity assessment, the performance of 20 FR, one fused FR, five RR, and 10 NR IQA methods is evaluated on four datasets (CSIQ [6], LIVE R2 [3], TID2008 [4], TID2013 [5]) in terms of PLCC, SRCC and RMSE.…”

Section: Introductionmentioning

confidence: 99%

“…4) Some surveys use a single dataset [3], [29], [30], which limits content diversity and raises concerns about the generalization of their findings. 5) None of the surveys evaluates the performance of fused FR methods with the exception of [34] which evaluates only a single FR fusion method. 6) Some surveys [32], [33] are specific to the evaluation of NR methods.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Comprehensive Performance Evaluation of Image Quality Assessment Algorithms

Athar

Zhou

2019

IEEE Access

View full text Add to dashboard Cite

Image quality assessment (IQA) algorithms aim to predict perceived image quality by human observers. Over the last two decades, a large amount of work has been carried out in the field. New algorithms are being developed at a rapid rate in different areas of IQA, but are often tested and compared with limited existing models using out-of-date test data. There is a significant gap when it comes to large-scale performance evaluation studies that include a wide variety of test data and competing algorithms. In this work we aim to fill this gap by carrying out the largest performance evaluation study so far. We test the performance of 43 full-reference (FR), seven fused FR (22 versions), and 14 no-reference (NR) methods on nine subject-rated IQA datasets, of which five contain singly distorted images and four contain multiply distorted content. We use a variety of performance evaluation and statistical significance testing criteria. Our findings not only point to the top performing FR and NR IQA methods, but also highlight the performance gap between them. In addition, we have also conducted a comparative study on FR fusion methods, and an important discovery is that rank aggregation based FR fusion is able to outperform not only other FR fusion approaches but also the top performing FR methods. It may be used to annotate IQA datasets as a possible alternative to subjective ratings, especially in situations where it is not possible to obtain human opinions, such as in the case of large-scale datasets composed of thousands or even millions of images.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Comprehensive Performance Evaluation of Image Quality Assessment Algorithms

Athar

Zhou

2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The meaning and the deeper relation of the link between information theory and aesthetic are to be further investigated in future work. Finding the most fundamental law or the optimization process that underlies aesthetically appealing patterns would be of great interest for the research in this area and for many applications [ 63 , 64 , 65 , 66 , 67 , 68 , 69 , 70 , 71 , 72 , 73 , 74 , 75 , 76 , 77 , 78 , 79 ]. It is interesting to see whether the proposed approach has any link to the aesthetic judgment mechanism in the brain, and how is that related to information theory.…”

Section: Discussionmentioning

confidence: 99%

An Information Theory Approach to Aesthetic Assessment of Visual Patterns

Khalili

Bouchachia

2021

Entropy

View full text Add to dashboard Cite

The question of beauty has inspired philosophers and scientists for centuries. Today, the study of aesthetics is an active research topic in fields as diverse as computer science, neuroscience, and psychology. Measuring the aesthetic appeal of images is beneficial for many applications. In this paper, we will study the aesthetic assessment of simple visual patterns. The proposed approach suggests that aesthetically appealing patterns are more likely to deliver a higher amount of information over multiple levels in comparison with less aesthetically appealing patterns when the same amount of energy is used. The proposed approach is evaluated using two datasets; the results show that the proposed approach is more accurate in classifying aesthetically appealing patterns compared to some related approaches that use different complexity measures.

show abstract

“…In this paper, we focus on image fidelity quality assessment and use IQA for image fidelity quality assessment when without introducing ambiguity. Please refer to the survey [5] for more details on aesthetics assessment and visual comfort assessment.…”

Section: Introductionmentioning

confidence: 99%

“…Despite the performance improvements achieved by the CNN-based IQA models, lacking training samples is one of the challenges for CNN-based objective IQA [5]- [7]. Existing CNN-based no-reference IQA models solve this problem by two types of methods.…”

Section: Introductionmentioning

confidence: 99%

Siamese-Network-Based Learning to Rank for No-Reference 2D and 3D Image Quality Assessment

et al. 2019

Self Cite

View full text Add to dashboard Cite

2D image quality assessment (IQA) and stereoscopic 3D IQA are considered as two different tasks in the literature. In this paper, we present an index for both no-reference 2D and 3D IQA. We propose to transform the IQA task into a task of quality comparison between images. By generating image pairs, the amount of training data reaches the square of the original amount of data, effectively solving the lacking of training samples. We also propose a learning to rank model using Siamese convolutional neural networks (LRSN) for quality comparison. The presented LRSN has two branches that have the same structure, share weights with each other, and take two image patches as inputs. The goal of LRSN is learning to rank the quality scores between the two input image patches. The relative quality score of a test image is obtained by first comparing its image patches with many image patches of other images and counts the number of times that its image patches are ranked superior to other patches. The experimental results on three 2D (LIVE, CSIQ, and TID2013) and three 3D (LIVE 3D Phase-I, LIVE 3D Phase-II, and NBU) IQA databases demonstrate that the proposed LRSN model works well for both 2D and 3D IQA and outperforms the state-of-the-art no-reference 2D and 3D IQA metrics. INDEX TERMS No-reference image quality assessment, stereoscopic image quality assessment, Siamese convolutional neural networks, learning to rank.

show abstract

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

Cited by 48 publications

References 126 publications

A Comprehensive Performance Evaluation of Image Quality Assessment Algorithms

A Comprehensive Performance Evaluation of Image Quality Assessment Algorithms

An Information Theory Approach to Aesthetic Assessment of Visual Patterns

Siamese-Network-Based Learning to Rank for No-Reference 2D and 3D Image Quality Assessment

Contact Info

Product

Resources

About