Video quality assessment based on structural distortion measurement

By Zhou Wang, Ligang Lu, A. Bovik. 2004

1,162 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Evaluation & Benchmarks

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Evaluation & Benchmarks

Citations in the corpus

Scaling Autoregressive Video Models (2019, methodology): “However, these metrics were developed for images and have serious ﬂaws when applied to videos (Wang et al., 2004a; Wang & Li, 2007; Zhang et al., 2018; Lee et al., 2018).”
An overview of multi-modal medical image fusion (2016, methodology): “SSIM metric is used as tools in evaluating the quality of images in video [46-49] and”
The Evolution of Video Quality Measurement: From PSNR to Hybrid Metrics (2008, background): “’s Structural Similarity (SSIM) index [22] computes the mean, variance and covariance of small patches inside a frame and combines the measurements into”
Multiscale structural similarity for image quality assessment (2003, background): “Structural similarityprovides an alternative and complementary approach to the problem of image quality assessment [3]– [6].”
Hypercomplex Quality Assessment of Multi/Hyperspectral Images (2009, positive): “However, this index has been developed to be applied to monochrome images, and to overcome this limitation, a weighted average of UQI indexes of color images can be carried out, as suggested in [5] and [6].”
From QoS to QoE: A Tutorial on Video Quality Assessment (2015, methodology): “The SSIM for image is extended to SSIM for video sequence in [87].”
F Mean Squared Error: Love It or Leave It? (2009, methodology): “More recent methods seek to detect motion and convert the motion information into spatiotemporal weighting factors in the pooling stage of video fidelity measurement [46], [50], [51].”
VSNR: A Wavelet-Based Visual Signal-to-Noise Ratio for Natural Images (2007, background): “Part of the reason these metrics fail is the fact that they operate based on the digital values of rather than on the physical luminances of the distortions ultimately emitted from the device on which the images are displayed.”
Study of Subjective and Objective Quality Assessment of Video (2010, methodology): “The SSIM index was applied frame-by-frame on the luminance component of the video [ 30 ] and the overall SSIM index for the video was computed as the average of the frame level quality scores.”
Blind Prediction of Natural Video Quality (2014, methodology): “Prominent FR-VQA algorithms include MOVIE [6], VSSIM [7], VQM [8], DVQ [9], Tetra VQM [10], ST-MAD [11], and the work in [12] and [13].”
Spatio-Temporal Just Noticeable Distortion Profile for Grey Scale Image/Video in DCT Domain (2009, result): “Since the human eyes are usually not sensitive to the distortion in the large motion frames [22], [24], [ 36 ], this result is consistent with the human visual system.”
Video Quality Assessment Using a Statistical Model of Human Visual Speed Perception (2007, methodology): “More detailed explanations and discussions about SSIM can be found in the referred papers [5, 6].”
UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content (2020, background): “tine source video to measure visual differences between a target signal and a corresponding reference [20]–[23], while”
Motion Tuned Spatio-Temporal Quality Assessment of Natural Videos (2010, methodology): “In [ 4 ]‐[6], motion information is only used to design weights to pool local spatial quality indices into a single quality score for the video.”
Information Content Weighting for Perceptual Image Quality Assessment (2011, methodology): “Combinations of different strategies have also shown to be a useful approach [19], [ 25 ], [26], [31].”
Perceptual Video Coding Based on SSIM-Inspired Divisive Normalization (2013, methodology): “To apply SSIM to all three color components, we combine the SSIM indices of these components by [56]”
A modified PSNR metric based on HVS for quality assessment of color images (2011, methodology): “Correlation of PSNRQ with different HVS based metrics like Edge Performance Index (EPI), Structural Correlation (SC), Mean Absolute Error (MAE) [14], CONTRAST (c(x,y)), and SSIM [5] has been calculated and it comes out to be 0.9953, 0.9971, 0.8267, 0.7385 and 0.9965 respectively.”