A universal image quality index

By Zhou Wang, A. Bovik. IEEE Signal Processing Letters, 2002

6,055 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/41227e1a654638b8a612f04d2030c94e37426f96

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 Media Technology

Citations in the corpus

Image De-Raining Using a Conditional Generative Adversarial Network (2017, methodology): “As the ground truth is available for the these test images, we calculate the quantitative measures such as PSNR, SSIM, UQI and VIF.”
Information Content Weighting for Perceptual Image Quality Assessment (2011, methodology): “domain methods such as the mean squared error (MSE) and the structural similarity (SSIM) index [4], [5] compute pixelor patch-wise distortion/quality measures in space, while block-discrete cosine transform [6] and wavelet-based [7]–[11] approaches define localized quality/distortion measures across”
IPOLE - semi-analytic scheme for relativistic polarized radiative transport (2017, methodology): “We find Qidx(I,Q,U,V)=(0.999968,0.999173,0.998880,0.995589), where Qidx=1 would mean that two images are identical, which confirms strong consistency between corresponding Stokes maps.”
From QoS to QoE: A Tutorial on Video Quality Assessment (2015, methodology): “In [76], when the SSIM was ﬁrst proposed, the parameters C 1 , C 2 , and C 3 are excluded.”
A Multiscale and Multidepth Convolutional Neural Network for Remote Sensing Imagery Pan-Sharpening (2017, background): “metric (Q) [45], the Erreur Relative Globale Adimensionnelle de Synthèse (ERGAS) [46], the spectral angle mapper (SAM) [47], and Q2n: An expanded version of Q that adds spectral fidelity into consideration [48].”
Sparse Gradient Regularized Deep Retinex Network for Robust Low-Light Image Enhancement (2021, methodology): “Since assessing the quality of enhanced images is not a trivial task, we adopt four evaluation metrics: Peak Signal-to-Noise Ratio (PSNR), Structural SIMilarity (SSIM) [55], Universal Quality Index (UQI) [56] and Optimal Scale Selection (OSS) [57].”
A Comparative Study for Single Image Blind Deblurring (2016, methodology): “For full-reference metrics, we choose several widely used metrics , PSNR and SSIM [40], as well as WSNR [22], MS- SSIM [41], IFC [37], NQM [4], UIQI [39], VIF [36].”
A Critical Comparison Among Pansharpening Algorithms (2015, background): “The definition of a technique that fulfills the constraints defined in the protocol is still an open problem [6], [37] and relates closely to the general discussion regarding image quality assessment [38] and image fusion [39], [40].”
A Convex Formulation for Hyperspectral Image Superresolution via Subspace-Based Regularization (2014, methodology): “The third index was based on the Universal Image Quality Index (UIQI), proposed by Wang et al. [53].”
TID2008 – A database for evaluation of full-reference visual quality assessment metrics (2004, methodology): “We have evaluated correspondence of HVS to the following 18 metrics (quality indices): MSSIM [8, 30], VIF [31, 30], a pixel based version of VIF (VIFP) [31, 30], VSNR [9, 30], PSNR-HVS (PSNRHVS) [28], PSNR-HVS-M (PSNRHVSM) [7], SSIM [6], NQM [32, 30], UQI [33], XYZ [34], LINLAB [35], IFC [36, 30], W”
Generative Adversarial Network in Medical Imaging: A Review (2018, background): “M13 Wang and Bovik (2002) UQI Universal quality index with regard to a given groundtruth M14 Zhang et al. (2011) FSIM A low-level feature based image quality assessment (IQA) metric with regard to a given groundtruth”
Evaluation of Sparse-view Reconstruction from Flat-panel-detector Cone-beam CT (2010, methodology): “We have also calculated data divergence D, convergence parameter cα and quantitative metrics UQI and MI at different iterations in which the convergence behavior of the ASD-POCS algorithm similar to that in figure 7 can be observed.”
Perceptual Quality Assessment for Multi-Exposure Image Fusion (2015, methodology): “Inspired by the SSIM index [27] for general-purpose IQA, Piella and Heijmans [22] developed three models to predict fused image quality based on the universal quality index [30].”
A survey of classical methods and new trends in pansharpening of multispectral images (2011, methodology): “The Universal Image Quality Index (UIQI) proposed in [110] can be considered a special case for SSIM index While these parameters only evaluate the difference in spectral information between each band of the merged and the reference image, in order to estimate the global spectral quality of the merg”