On Advances in Statistical Modeling of Natural Images

By Akansha Srivastava, A. B. Lee, Eero P. Simoncelli, S.-C. Zhu. Journal of Mathematical Imaging and Vision, 2004

568 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/097e157201da1c6abd06eb92c80de5e6762994d8

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

Citations in the corpus

Image information and visual quality (2006, background): “Many researchers have attempted to understand the structure of this subspace of natural images by studying their statistics (a review on natural scene models could be found in [19]).”
No-Reference Image Quality Assessment in the Spatial Domain (2012, background): “The regularity of natural scene statistics (NSS) has been well established in the visual science literature, where regularity has been demonstrated in the spatial domain [15], and in the wavelet domain [16].”
No-reference quality assessment using natural scene statistics: JPEG2000 (2005, methodology): “A review of recent NSS models is presented in [33] .”
Spontaneous and driven cortical activity: implications for computation. (2009, unknown): “In general, however, the manifold of natural signals is not simple a circle but could be much more complicated (Figure 1d) [36 ,37,38], yet all the same ideas apply.”
Blind Image Quality Assessment: A Natural Scene Statistics Approach in the DCT Domain (2012, methodology): “The Laplacian model has often been used to approximate the distribution of DCT image coefficients [30].”
AI Art and its Impact on Artists (2023, background): “Early approaches to image synthesis such as [38, 95, 120], aimed to achieve texture synthesis, i.e. modifying an existing image to copy the texture of another image [38, 95, 120].”
Blind Image Quality Assessment: From Natural Scene Statistics to Perceptual Quality (2011, methodology): “We have developed a computational theory for NR IQA based on the statistics of natural images1 [7], [8], [9], [10].”
From learning models of natural image patches to whole image restoration (2011, background): “There are many work which attempt to explain this and related phenomena [2, 3, 18] and among those the “Dead Leaves” model is especially important [19, 18, 20, 2].”
ViBe: A Universal Background Subtraction Algorithm for Video Sequences (2011, background): “Finally, it should be noted that the statistical relevance of a Gaussian model is debatable as some authors claim that natural images exhibit non-Gaussian statistics [54].”
Visual Saliency Based on Scale-Space Analysis in the Frequency Domain (2013, unknown): “We refer to these patterns as being non-salient.”
KonIQ-10k: An Ecologically Valid Database for Deep Learning of Blind Image Quality Assessment (2019, methodology): “Many conventional BIQA methods were derived from the Natural Scene Statistics (NSS) model [31].”
Model distortions in Bayesian MAP reconstruction (2007, background): “Realistic statistical modeling of the physical phenomena in data-acquisition devices on the one hand, and modeling of the priors for real-world images and signals on the other hand, focuses more and more efforts in research and applications, and the references are abundant [3, 7, 31, 52, 39, 57, 54,”
Fields of Experts (2009, background): “These statistics, as well as the study of the statistics of natural images in general have received a lot of attention in the literature (Ruderman, 1994; Olshausen and Field, 1996; Huang and Mumford, 1999; Srivastava et al., 2003).”
A Mathematical Motivation for Complex-Valued Convolutional Networks (2015, background): “…in the original work of Daubechies (1992), Meyer (1993), Coifman et al. (1994), Coifman and Donoho (1995), Simoncelli and Freeman (1995), Meyer and Coifman (1997), LeCun et al. (1998), Donoho et al. (2003), Srivastava et al. (2003), Rabiner and Schafer (2007), and Mallat (2008), for example.”
Perceptual quality prediction on authentically distorted images using a bag of features approach (2016, background): “The feature maps are also strongly motivated by recent NSS models (Mittal, Moorthy, & Bovik, 2012; Zhang et al., 2014; Ruderman, 1994; Srivastava, Lee, Simoncelli, & Zhu, 2003) of natural and distorted pictures that are dual to low-level perceptual processing models.”