Comparison of objective quality models for adaptive bit-streaming services

Lee, C.; Woo, Seongyoun; Baek, Seungyong; Han, Jeong Hye; Chae, Ju Byung; Rim, Jaesung

doi:10.1109/iisa.2017.8316385

Cited by 20 publications

(5 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have to mention that the results given by the VMAF are not biased by the image content or by the frame size, as its results are consistent through different frame sizes and content. A good correlation with the DMOS and MOS values of the VMAF has been reported [35]- [37], showing that it can be considered a robust metric. Notice that although the behavior shown in Figure 5 seems to say that the VMAF metric does not correctly assess the perceived quality when both filters are disabled, it shows good results when only the DB filter is enabled.…”

Section: Discussionmentioning

confidence: 94%

“…Other works in the literature use VMAF: (a) in [35], the authors proved a strong correlation between subjective DMOS studies and the VMAF values obtained for a set of 4K sequences, (b) in [36], the authors also show a high correlation with the MOS values obtained for HD and UHD content, and (c) in [37], an analysis of different quality metrics for multi-resolution adaptive streaming showed that VMAF obtained the highest correlation with perceptual quality.…”

Section: Due To the Fact That The Bd-rate Calculationmentioning

confidence: 95%

See 1 more Smart Citation

Analysis of the Perceptual Quality Performance of Different HEVC Coding Tools

et al. 2021

View full text Add to dashboard Cite

Each new video encoding standard includes encoding techniques that aim to improve the performance and quality of the previous standards. During the development of these techniques, PSNR was used as the main distortion metric. However, the PSNR metric does not consider the subjectivity of the human visual system, so that the performance of some coding tools is questionable from the perceptual point of view. To further explore this point, we have developed a detailed study about the perceptual sensibility of different HEVC video coding tools. In order to perform this study, we used some popular objective quality assessment metrics to measure the perceptual response of every single coding tool. The conclusion of this work will help to determine the set of HEVC coding tools that provides, in general, the best perceptual response.

show abstract

Section: Discussionmentioning

confidence: 94%

Section: Due To the Fact That The Bd-rate Calculationmentioning

confidence: 95%

Analysis of the Perceptual Quality Performance of Different HEVC Coding Tools

et al. 2021

View full text Add to dashboard Cite

show abstract

“…In addition, we used an array of metrics developed by the image/video processing community that are supposed to approximate human quality assessments [26]. We tested six among the most widely adopted metrics in the image quality assessment field, Peak signal to noise ratio (PSNR), Structural Similarity Index (SSIM), Structural Similarity Index (MS-SSIM), Video Multimethod Assessment Fusion (VMAF), Natural Image Quality Evaluator (NIQE), Blind/referenceless image spatial quality evaluator (BRISQUE); see [40] for a review). In the following, each of these metrics is introduced in more detail.…”

Section: Image Quality Metricsmentioning

confidence: 99%

Quality assessment of anatomical MRI images from generative adversarial networks: Human assessment and image quality metrics

Treder

Codrai

Tsvetanov

2022

Journal of Neuroscience Methods

View full text Add to dashboard Cite

“…Detail Loss Metric (DLM) [15], and motion. In practice, the industry usually uses the VMAF metric extensively because of its superior accuracy compared to traditional metrics [16][17][18].…”

Section: Introductionmentioning

confidence: 99%

Learning Adaptive Quantization Parameter for Consistent Quality Oriented Video Coding

Vu,

Do,

Nguyen

et al. 2023

Electronics

View full text Add to dashboard Cite

In the industry 4.0 era, video applications such as surveillance visual systems, video conferencing, or video broadcasting have been playing a vital role. In these applications, for manipulating and tracking objects in decoded video, the quality of decoded video should be consistent because it largely affects the performance of the machine analysis. To cope with this problem, we propose a novel perceptual video coding (PVC) solution in which a full reference quality metric named video multimethod assessment fusion (VMAF) is employed together with a deep convolutional neural network (CNN) to obtain consistent quality while still achieving high compression performance. First of all, in order to achieve the consistent quality requirement, we propose a CNN model with an expected VMAF as input to adaptively adjust the quantization parameters (QP) for each coding block. Afterwards, to increase the compression performance, a Lagrange coefficient of rate-distortion optimization (RDO) mechanism is adaptively computed according to rate-QP and quality-QP models. The experimental results show that the proposed PVC solution has achieved two targets simultaneously: the quality of video sequence is kept consistently with an expected quality level and the bit rate saving of the proposed method is higher than traditional video coding standards and the relevant benchmark, notably with around 10% bitrate saving on average.

show abstract

Comparison of objective quality models for adaptive bit-streaming services

Cited by 20 publications

References 6 publications

Analysis of the Perceptual Quality Performance of Different HEVC Coding Tools

Analysis of the Perceptual Quality Performance of Different HEVC Coding Tools

Quality assessment of anatomical MRI images from generative adversarial networks: Human assessment and image quality metrics

Learning Adaptive Quantization Parameter for Consistent Quality Oriented Video Coding

Contact Info

Product

Resources

About