Visible differences predictor: an algorithm for the assessment of image fidelity

By Scott J. Daly. 1992

Subfields: Computer Vision and Pattern Recognition

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. Dacheng Tao
2. Luc Van Gool
3. Lei Zhang
4. Ming-Hsuan Yang
5. A. Bovik
6. Chen Change Loy
7. Zhou Wang
8. Bernt Schiele

Citations in the corpus

• Generating Images with Perceptual Similarity Metrics based on Deep Networks (2016, background): “These go beyond simple distances in image space and can capture complex and perceptually important properties of images.”
• Seven Challenges in Image Quality Assessment: Past, Present, and Future Research (2013, background): “Note that learning effects have been shown to lower the slopes of the TvC curves [87, 90].”
• Image quality assessment based on a degradation model (2000, background): “Daly’s visible differences predictor [ 5 ] assesses still image quality using a nonlinear HVS model consisting of an amplitude nonlinearity, a lowpass CSF, and a hierarchy of detectors.”
• Fully Deep Blind Image Quality Predictor (2017, background): “Based on these analyses on the HVS, a number of FR-IQA metrics have been developed [10].”
• Learning to generate images with perceptual similarity metrics (2015, methodology): “Some are built on complex models of the human visual system, such as the Sarnoff JND model [23], the visual differences predictor [5], the moving picture quality metric [31], the perceptual distortion metric [35], and the metric of [10].”
• The Evolution of Video Quality Measurement: From PSNR to Hybrid Metrics (2008, unknown): “Later well-known metrics in this category are the Visual Differences Predictor (VDP) by Daly [17], the Sarnoff JND (just noticeable differences) metric by Lubin [18], van den Branden Lambrecht’s Moving Picture Quality Metric (MPQM) [19], and the author’s own perceptual distortion metric (PDM) [20].”
• Visual equivalence: towards a new standard for image fidelity (2007, methodology): “Existing methods typically incorporate visible differences predictors (VDPs) [Daly 1993] to determine when an approximate so-lution will be visually indistinguishable from a reference solution.”
• A Statistical Evaluation of Recent Full Reference Image Quality Assessment Algorithms (2006, unknown): “In [6], two famous visible difference predictors, by Daly [7] and Lubin [8], have been comparatively evaluated.”
• Display adaptive tone mapping (2008, methodology): “In fact most of the visual models, employed to estimate perceived image difference [Lu-bin and Pica 1991; Daly 1993] or to drive a tone mapping operator [Pattanaik et al. 1998], operate on image contrast.”
• Deep CNN-Based Blind Image Quality Predictor (2019, background): “example, the visual sensitivity of the HVS varies according to spatial frequency of stimuli [7], [8], and the presence of texture hinders other spatially coincident image changes [9].”
• An SVD-based grayscale image quality measure for local and global assessment (2006, background): “Furthermore, several papers present comparative evaluations of a number of selected measures for image compression [14], [16], [28], [31], [40], [44], and for noise and blur [13], [45].”