Visual quality assessment : recent developments, coding applications and future trends
01 Jan 2013-Vol. 2
TL;DR: This work provides an in-depth review of recent developments in the field of visual quality assessment and puts equal emphasis on video quality databases and metrics as this is a less investigated area.
Abstract: Research on visual quality assessment has been active during the last decade. In this work, we provide an in-depth review of recent developments in the field. As compared with existing survey papers, our current work has several unique contributions. First, besides image quality databases and metrics, we put equal emphasis on video quality databases and metrics as this is a less investigated area. Second, we discuss the application of visual quality evaluation to perceptual coding as an example for applications. Third, we benchmark the performance of state-of-the-art visual quality metrics with experiments. Finally, future trends in visual quality assessment are discussed.
Citations
More filters
TL;DR: This work explores a novel foveated reconstruction method that employs the recent advances in generative adversarial neural networks to reconstruct a plausible peripheral video from a small fraction of pixels provided every frame.
Abstract: In order to provide an immersive visual experience, modern displays require head mounting, high image resolution, low latency, as well as high refresh rate. This poses a challenging computational problem. On the other hand, the human visual system can consume only a tiny fraction of this video stream due to the drastic acuity loss in the peripheral vision. Foveated rendering and compression can save computations by reducing the image quality in the peripheral vision. However, this can cause noticeable artifacts in the periphery, or, if done conservatively, would provide only modest savings. In this work, we explore a novel foveated reconstruction method that employs the recent advances in generative adversarial neural networks. We reconstruct a plausible peripheral video from a small fraction of pixels provided every frame. The reconstruction is done by finding the closest matching video to this sparse input stream of pixels on the learned manifold of natural videos. Our method is more efficient than the state-of-the-art foveated rendering, while providing the visual experience with no noticeable quality degradation. We conducted a user study to validate our reconstruction method and compare it against existing foveated rendering and video compression techniques. Our method is fast enough to drive gaze-contingent head-mounted displays in real time on modern hardware. We plan to publish the trained network to establish a new quality bar for foveated rendering and compression as well as encourage follow-up research.
104 citations
Cites methods from "Visual quality assessment : recent ..."
...…Similarity Index (SSIM) [Wang et al. 2004], Video Quality Metric (VQM) [Pinson and Wolf 2004], and Spatio-Temporal Reduced Reference Entropic Differencing (ST-RRED) [Soundararajan and Bovik 2013] have been successfully predicting human subjective performance in the fovea [Liu et al. 2013]....
[...]
TL;DR: An ensemble method for full-reference image quality assessment (IQA) based on the parallel boosting (ParaBoost) idea is proposed, which outperforms existing IQA methods by a significant margin.
Abstract: An ensemble method for full-reference image quality assessment (IQA) based on the parallel boosting (ParaBoost) idea is proposed in this paper. We first extract features from existing image quality metrics and train them to form basic image quality scorers (BIQSs). Then, we select additional features to address specific distortion types and train them to construct auxiliary image quality scorers (AIQSs). Both BIQSs and AIQSs are trained on small image subsets of certain distortion types and, as a result, they are weak performers with respect to a wide variety of distortions. Finally, we adopt the ParaBoost framework, which is a statistical scorer selection scheme for support vector regression (SVR), to fuse the scores of BIQSs and AIQSs to evaluate the images containing a wide range of distortion types. This ParaBoost methodology can be easily extended to images of new distortion types. Extensive experiments are conducted to demonstrate the superior performance of the ParaBoost method, which outperforms existing IQA methods by a significant margin. Specifically, the Spearman rank order correlation coefficients (SROCCs) of the ParaBoost method with respect to the LIVE, CSIQ, TID2008, and TID2013 image quality databases are 0.98, 0.97, 0.98, and 0.96, respectively.
71 citations
Cites background from "Visual quality assessment : recent ..."
...Recently, the learning-based approach emerges as a strong competitor in the image quality assessment (IQA) field since it is difficult to predict visual quality under various distortion types and rich image contents using a single formula [10], [11]....
[...]
01 Dec 2014
TL;DR: This work studies the visual quality of streaming video and proposes a fusion-based video quality assessment (FVQA) index, where fusion coefficients are learned from training video samples in the same group to predict its quality.
Abstract: In this work, we study the visual quality of streaming video and propose a fusion-based video quality assessment (FVQA) index to predict its quality. In the first step, video sequences are grouped according to their content complexity to reduce content diversity within each group. Then, at the second step, several existing video quality assessment methods are fused to provide the final video quality score, where fusion coefficients are learned from training video samples in the same group. We demonstrate the superior performance of FVQA as compared with other video quality assessment methods using the MCL-V video quality database.
61 citations
Cites background from "Visual quality assessment : recent ..."
...Since PSNR is not well correlated with subjective human visual experience, other VQA indices are proposed to assess video quality [8]....
[...]
TL;DR: Under a new framework, a comprehensive description of existing metrics, their strengths, their weaknesses, and a detailed performance analysis on real images from public image inpainting database are provided.
54 citations
TL;DR: A no-reference (NR) learning-based approach to assess image quality is presented, and the proposed NR image quality assessment models are robust with respect to more than 24 image distortion types.
Abstract: A no-reference (NR) learning-based approach to assess image quality is presented in this paper. The devised features are extracted from wide perceptual domains, including brightness, contrast, color, distortion, and texture. These features are used to train a model (scorer) which can predict scores. The scorer selection algorithms are utilized to help simplify the proposed system. In the final stage, the ensemble method is used to combine the prediction results from selected scorers. Two multiple-scale versions of the proposed approach are also presented along with the single-scale one. They turn out to have better performances than the original single-scale method. Because of having features from five different domains at multiple image scales and using the outputs (scores) from selected score prediction models as features for multi-scale or cross-scale fusion (i.e., ensemble), the proposed NR image quality assessment models are robust with respect to more than 24 image distortion types. They also can be used on the evaluation of images with authentic distortions. The extensive experiments on three well-known and representative databases confirm the performance robustness of our proposed model.
54 citations
Cites methods from "Visual quality assessment : recent ..."
...As we know, formula-based approaches only can target at a very narrow range of distortion types and predict the visual quality well within 1 to 2 distortion types [12]....
[...]
References
More filters
TL;DR: In this article, a structural similarity index is proposed for image quality assessment based on the degradation of structural information, which can be applied to both subjective ratings and objective methods on a database of images compressed with JPEG and JPEG2000.
Abstract: Objective methods for assessing perceptual image quality traditionally attempted to quantify the visibility of errors (differences) between a distorted image and a reference image using a variety of known properties of the human visual system. Under the assumption that human visual perception is highly adapted for extracting structural information from a scene, we introduce an alternative complementary framework for quality assessment based on the degradation of structural information. As a specific example of this concept, we develop a structural similarity index and demonstrate its promise through a set of intuitive examples, as well as comparison to both subjective ratings and state-of-the-art objective methods on a database of images compressed with JPEG and JPEG2000. A MATLAB implementation of the proposed algorithm is available online at http://www.cns.nyu.edu//spl sim/lcv/ssim/.
40,609 citations
09 Nov 2003
TL;DR: This paper proposes a multiscale structural similarity method, which supplies more flexibility than previous single-scale methods in incorporating the variations of viewing conditions, and develops an image synthesis method to calibrate the parameters that define the relative importance of different scales.
Abstract: The structural similarity image quality paradigm is based on the assumption that the human visual system is highly adapted for extracting structural information from the scene, and therefore a measure of structural similarity can provide a good approximation to perceived image quality. This paper proposes a multiscale structural similarity method, which supplies more flexibility than previous single-scale methods in incorporating the variations of viewing conditions. We develop an image synthesis method to calibrate the parameters that define the relative importance of different scales. Experimental comparisons demonstrate the effectiveness of the proposed method.
4,333 citations
TL;DR: A novel feature similarity (FSIM) index for full reference IQA is proposed based on the fact that human visual system (HVS) understands an image mainly according to its low-level features.
Abstract: Image quality assessment (IQA) aims to use computational models to measure the image quality consistently with subjective evaluations. The well-known structural similarity index brings IQA from pixel- to structure-based stage. In this paper, a novel feature similarity (FSIM) index for full reference IQA is proposed based on the fact that human visual system (HVS) understands an image mainly according to its low-level features. Specifically, the phase congruency (PC), which is a dimensionless measure of the significance of a local structure, is used as the primary feature in FSIM. Considering that PC is contrast invariant while the contrast information does affect HVS' perception of image quality, the image gradient magnitude (GM) is employed as the secondary feature in FSIM. PC and GM play complementary roles in characterizing the image local quality. After obtaining the local quality map, we use PC again as a weighting function to derive a single quality score. Extensive experiments performed on six benchmark IQA databases demonstrate that FSIM can achieve much higher consistency with the subjective evaluations than state-of-the-art IQA metrics.
4,028 citations
TL;DR: An image information measure is proposed that quantifies the information that is present in the reference image and how much of this reference information can be extracted from the distorted image and combined these two quantities form a visual information fidelity measure for image QA.
Abstract: Measurement of visual quality is of fundamental importance to numerous image and video processing applications. The goal of quality assessment (QA) research is to design algorithms that can automatically assess the quality of images or videos in a perceptually consistent manner. Image QA algorithms generally interpret image quality as fidelity or similarity with a "reference" or "perfect" image in some perceptual space. Such "full-reference" QA methods attempt to achieve consistency in quality prediction by modeling salient physiological and psychovisual features of the human visual system (HVS), or by signal fidelity measures. In this paper, we approach the image QA problem as an information fidelity problem. Specifically, we propose to quantify the loss of image information to the distortion process and explore the relationship between image information and visual quality. QA systems are invariably involved with judging the visual quality of "natural" images and videos that are meant for "human consumption." Researchers have developed sophisticated models to capture the statistics of such natural signals. Using these models, we previously presented an information fidelity criterion for image QA that related image quality with the amount of information shared between a reference and a distorted image. In this paper, we propose an image information measure that quantifies the information that is present in the reference image and how much of this reference information can be extracted from the distorted image. Combining these two quantities, we propose a visual information fidelity measure for image QA. We validate the performance of our algorithm with an extensive subjective study involving 779 images and show that our method outperforms recent state-of-the-art image QA algorithms by a sizeable margin in our simulations. The code and the data from the subjective study are available at the LIVE website.
3,146 citations
TL;DR: This article has reviewed the reasons why people want to love or leave the venerable (but perhaps hoary) MSE and reviewed emerging alternative signal fidelity measures and discussed their potential application to a wide variety of problems.
Abstract: In this article, we have reviewed the reasons why we (collectively) want to love or leave the venerable (but perhaps hoary) MSE. We have also reviewed emerging alternative signal fidelity measures and discussed their potential application to a wide variety of problems. The message we are trying to send here is not that one should abandon use of the MSE nor to blindly switch to any other particular signal fidelity measure. Rather, we hope to make the point that there are powerful, easy-to-use, and easy-to-understand alternatives that might be deployed depending on the application environment and needs. While we expect (and indeed, hope) that the MSE will continue to be widely used as a signal fidelity measure, it is our greater desire to see more advanced signal fidelity measures being used, especially in applications where perceptual criteria might be relevant. Ideally, the performance of a new signal processing algorithm might be compared to other algorithms using several fidelity criteria. Lastly, we hope that we have given further motivation to the community to consider recent advanced signal fidelity measures as design criteria for optimizing signal processing algorithms and systems. It is in this direction that we believe that the greatest benefit eventually lies.
2,601 citations
"Visual quality assessment : recent ..." refers background or methods in this paper
...However, they often correlate poorly with subjective visual quality [95]....
[...]
...Since SSIM is sensitive to relative translations, rotations, and scalings of images [95], complex-wavelet SSIM (CWSSIM) [100] has been developed....
[...]