Image information and visual quality

By Hamid R. Sheikh, A. Bovik. 2006

4,254 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

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

The Perception-Distortion Tradeoff (2017, methodology): “Many alternative, more perceptual, distortion measures have been proposed, including SSIM [40], MS-SSIM [42], IFC [36], VIF [35], VSNR [3] and FSIM [47].”
Pros and Cons of GAN Evaluation Measures (2018, neutral): “In addition to the above mentioned image quality measures, some other metrics such as Universal Quality Index (UQI) [87] and Visual Information Fidelity (VIF) [71] have also been adopted for assessing the quality of synthesized images.”
Blind Image Quality Assessment via Deep Learning (2015, methodology): “Four traditional full-reference IQA methods, PSNR, SSIM [38], IFC [39], and VIF [40], are used as the benchmark.”
Subjective evaluation of stereoscopic image quality (2013, methodology): “algorithms when used for 2D quality assessment [36].”
An Experiment-Based Review of Low-Light Image Enhancement Methods (2020, methodology): “For the FIQA-based evaluation, eleven metrics were selected, namely, MSE, PSNR, SSIM [301], LOE [136], PCQI [302], GMSD [304], VIF [305], VSI [306], FSIM [308], RVSIM [313], and IFC [314].”
Waterloo Exploration Database: New Challenges for Image Quality Assessment Models (2017, methodology): “MS-SSIM [43], VIF [9] and GMSD [10] are not tested here because they are used in the DIP generation process and thus are not independent of the test.”
Visual Importance Pooling for Image Quality Assessment (2009, methodology): “VIF is an alternate approach to IQA based on Natural Scene Statistics (NSS); however, in [8], it has been demonstrated that the SSIM and VIF metrics are equivalent.”
Modern Image Quality Assessment (2006, methodology): “Information-theoretic image quality assessment algorithms, as exemplified by the VIF Index (or Sheikh-Bovik Index), as reported in [72, 78] and in the large”
UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content (2020, background): “These natural scene statistics (NSS) models predictably deviate in the presence of distortions, thereby characterizing perceived quality degradations [47].”
MBLLEN: Low-Light Image/Video Enhancement Using CNNs (2018, methodology): “To evaluate the performance of different methods from different aspects and in a more fair way, we use a variety of different metrics, including PSNR, SSIM [39], Average Brightness(AB) [6], Visual Information Fidelity(VIF) [32], Lightness order error(LOE) as suggested in [41] and TMQI [40].”
RRED Indices: Reduced Reference Entropic Differencing for Image Quality Assessment (2012, methodology): “Information-theoretic methods for QA have produced some of the best performing FR QA algorithms, including the information fidelity criterion (IFC) [22] and the VIF index [3].”
Single Image Deraining using Scale-Aware Multi-Stage Recurrent Network (2017, methodology): “To quantitatively evaluate these methods, four evaluation metrics are used: Peak Signal-to-Noise Ratio (PSNR) [10], Structure Similarity Index (SSIM) [22], Visual Information Fidelity (VIF) [19], and Feature Similarity Index (FSIM) [24].”
Loss Functions for Image Restoration With Neural Networks (2017, background): “Another is the Visual Information Fidelity (VIF), which is based on the amount of shared information between the reference and distorted image [21].”
2018 PIRM Challenge on Perceptual Image Super-resolution (2018, methodology): “Note that we also tested the full-reference measures VIF [32], FSIM [49] and MS-SSIM [46], and the no-reference measures CORNIA [48] and BLIINDS [30], which all failed to correctly assess the perceptual quality(4).”
Learning to Incorporate Structure Knowledge for Image Inpainting (2020, methodology): “…take L 1 loss, peak signal-to-noise ratio (PSNR), structural similarity index (SSIM) (Wang et al. 2004), universal quality index (UQI) (Wang and Bovik 2002), visual information ﬁdelity (VIF) (Sheikh and Bovik 2006) and Frechet Inception Distance (FID) (Heusel et al. 2017) as our evaluation metrics.”
A Patch-Structure Representation Method for Quality Assessment of Contrast Changed Images (2015, methodology): “We compare the proposed method with both classical and state-of-the-art FR quality assessment algorithms, including PSNR, SSIM [6], MS-SSIM [10], IW-SSIM [11], GSIM [12], FSIM [13], GMSD [14], VSI [15] and VIF [16].”