Information Content Weighting for Perceptual Image Quality Assessment

By Zhou Wang, Qiang Li. IEEE Transactions on Image Processing, 2011

1,316 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/390666fa09f53c1ea9be6d4b3a89d87109b179b1

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

1. Lei Zhang
2. Xiaokang Yang
3. Dacheng Tao
4. Kede Ma
5. Weisi Lin
6. Guangtao Zhai
7. Luc Van Gool
8. Ming-Hsuan Yang

In Media Technology

1. Kede Ma
2. Weisi Lin
3. Guangtao Zhai
4. Ke Gu
5. Zhou Wang
6. Xiaokang Yang
7. Lei Zhang
8. A. Bovik

Citations in the corpus

• KADID-10k: A Large-scale Artificially Distorted IQA Database (2019, neutral): “By changing [14] 0.801 0.802 0.609 IWSSIM [15] 0.846 0.850 0.666 MDSI [16] 0.873 0.872 0.682 VSI [17] 0.878 0.879 0.691 FSIM [18] 0.851 0.854 0.665 GMSD [19] 0.847 0.847 0.664 SFF [20] 0.862 0.862 0.675 SCQI [21] 0.853 0.854 0.662 ADD-GSIM [22] 0.817 0.818 0.621 SR-SIM [23] 0.834 0.839 0.652 N R -”
• On the Mathematical Properties of the Structural Similarity Index (2012, background): “…similarity index [10] significantly and consistently outperformed MSE and its direct derivative, the peak signal-to-noise ratio, in terms of correlations with subjective image quality evaluations in extensive tests using a number of independent large-scale subject-rated image databases [6], [10].”
• Using Free Energy Principle For Blind Image Quality Assessment (2015, methodology): “The DCT and DWT decompositions have been widely applied in existing IQA models [4], [7], [10], [32].”
• Perceptual Quality Assessment for Multi-Exposure Image Fusion (2015, background): “These include information theoretic and natural scene statistical approaches [38]–[40], the adaptive linear system decomposition framework [41]–[43], the feature similarity method [44], and visual attention and saliency-based approaches [39], [45]–[47].”
• Gradient Magnitude Similarity Deviation: A Highly Efficient Perceptual Image Quality Index (2013, background): “However, the computation of phase congruency features is very costly.”
• Using labeled data to evaluate change detectors in a multivariate streaming environment (2009, neutral): “EDANet [17] also utilizes the strategy of dense connection, and the difference is that EDANet adopts the dense connection between modules using asymmetric convolution.”
• Image Quality Assessment Based on Gradient Similarity (2012, neutral): “, the SSIM for each image block) [1] or calculated as the IW average of the local SSIM [32].”
• Image database TID 2013 : Peculiarities , results and perspectives (2016, methodology): “Correspondence to HVS has been evaluated for the following metrics (quality indices): SFF [44], componentwise FSIM and its color version FSIMc [20], PSNR-HA and PSNR-HMA [43], SR-SIM [45], MSSIM [46], MAD index [27], IW-SSIM [19], MSDDM [47], IW-PSNR [19], color version of PSNR which takes into acco”
• Color image database TID2013: Peculiarities and preliminary results (2013, methodology): “The achieved performances have been utilized for a better understanding of drawbacks of the analyzed metrics and stimulated the design of new metrics and/or improvement (modification) of existing ones [6, 9-11].”
• Image Quality Assessment: Unifying Structure and Texture Similarity (2020, methodology): “Other design methodologies for knowledge-driven IQA include informationtheoretic criterion [4] and perception-based pooling [26].”
• Loss Functions for Neural Networks for Image Processing (2015, methodology): “One of these is the Information Weigthed SSIM (IW-SSIM), a modification of MS-SSIM that also includes a weighting scheme proportional to the local image information [20].”
• A Feature-Enriched Completely Blind Image Quality Evaluator (2015, background): “More details regarding the underpinnings of these two performance metrics can be found in [40].”
• Seven Challenges in Image Quality Assessment: Past, Present, and Future Research (2013, background): “In [203], Wang and Li argued that the optimal perceptual weights for pooling the output of an IQA algorithm across space should be proportional to the local information content, which is estimated in [203] by using statistical models of natural scenes.”
• Perceptual Video Coding Based on SSIM-Inspired Divisive Normalization (2013, background): “Since the clearly visible distortion regions will be perceptually more apparent [50], transforming all the coefficients into the perceptually uniform domain is also a convenient approach to improve the perceptual quality according to the philosophy behind distortion-based pooling scheme [51].”
• The Analysis of Image Contrast: From Quality Assessment to Automatic Enhancement (2016, methodology): “ods have been designed to pursue better performance [7], [8].”
• Objective Quality Assessment of Tone-Mapped Images (2013, methodology): “Following the idea used in multi-scale [16] and information-weighted SSIM [17], we adopt a multi-scale approach, where the images are iteratively low-pass filtered and downsampled to create an image pyramid structure [27], as illustrated in Fig.”
• A Patch-Structure Representation Method for Quality Assessment of Contrast Changed Images (2015, methodology): “The PCQI map produced by the proposed method also indicates local quality variations, which are useful in guiding the future design of advanced image enhancement algorithms.”
• Loss Functions for Image Restoration With Neural Networks (2017, methodology): “One of these is the Information Weigthed SSIM (IW-SSIM), a modification of MS-SSIM that also includes a weighting scheme proportional to the local image information [20].”