Reduced-Reference Image Quality Assessment Using Divisive Normalization-Based Image Representation

By Qiang Li, Zhou Wang. 2009

358 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

1. A. Bovik
2. Lei Zhang
3. Dacheng Tao
4. Kede Ma
5. Radu Timofte
6. Chen Change Loy
7. Zhou Wang
8. Luc Van Gool

In Media Technology

1. A. Bovik
2. Kede Ma
3. Zhou Wang
4. Jongyoo Kim
5. Sanghoon Lee
6. Lei Zhang
7. Damon M. Chandler
8. Tomer Michaeli

Citations in the corpus

• The Perception-Distortion Tradeoff (2017, methodology): “For example, [41, 43, 21] proposed a perceptual quality index based on the Kullback-Leibler (KL) divergence between the distribution of the wavelet coefficients of x̂ and that of natural scenes.”
• dipIQ: Blind Image Quality Assessment by Learning-to-Rank Discriminable Image Pairs (2017, background): “Therefore, statistics of raw [4], [6], [46], [47] and normalized [48], [49] wavelet coefficients, and wavelet coefficient correlations in the neighborhood [10], [29], [50]–[52] can be individually or jointly modeled as image naturalness measurements.”
• From QoS to QoE: A Tutorial on Video Quality Assessment (2015, methodology): “In [128], an SSIM-like metric largely based on [124], [133] and structural similarity is developed.”
• Information Content Weighting for Perceptual Image Quality Assessment (2011, methodology): “Inspired by several recent successful approaches in image denoising [36] and IQA [34], [37], [38], here we adopt the Gaussian scale mixture (GSM) model for natural images.”
• Fully Deep Blind Image Quality Predictor (2017, background): “Note that local normalization has been adopted successfully in a number of IQA studies [11], [32], [33], [49] and machine learning [50].”
• End-to-End Blind Image Quality Assessment Using Deep Neural Networks (2018, methodology): “In BRISQUE [4], inspired by earlier work on reduced-reference (RR) IQA using local gain control based divisive normalization [26], natural scene statistics (NSS) are extracted from locally normalized luminance coeffi-”
• RRED Indices: Reduced Reference Entropic Differencing for Image Quality Assessment (2012, methodology): “The most successful general purpose RR quality metrics are based on computing the KL divergence between the reference and test images [12].”
• Perceptual Video Coding Based on SSIM-Inspired Divisive Normalization (2013, background): “It is shown to be a useful framework that accounts for the masking effect in the HVS, which refers to the reduction of the visibility of an image component in the presence of neighboring components [35], [36].”
• A reduced-reference perceptual image and video quality metric based on edge preservation (2012, methodology): “For the images in the LIVE database our metric outperforms the considered state-of-the-art RR metrics in all the considered scenarios, except for the case of WN, where the metric [15] performs better at the expense of a higher complexity, and the case of JPEG2000 where the benchmark RR metric [4], b”
• Blind Image Quality Assessment: A Natural Scene Statistics Approach in the DCT Domain (2012, methodology): “The generalized Gaussian model has recently been used as a feature in a NSS-based RR-IQA algorithm [21] and in a simple two-stage NR-IQA algorithm in [15].”
• No-Reference Image Quality Assessment in the Spatial Domain (2012, neutral): “MSCN(i,j)”
• Blind Image Quality Assessment: From Natural Scene Statistics to Perceptual Quality (2011, methodology): “Here, divisive normalization is implemented as described in [3].”
• Seven Challenges in Image Quality Assessment: Past, Present, and Future Research (2013, methodology): “In [288], Li and Wang presented an RR algorithm based on a divisive normalization image representation.”
• Unsupervised feature learning framework for no-reference image quality assessment (2012, methodology): “For RR-IQA, partial information of reference image is necessary for computing the quality measure [8].”