A Parametric Texture Model Based on Joint Statistics of Complex Wavelet Coefficients
Citations
6,759 citations
4,888 citations
Cites methods from "A Parametric Texture Model Based on..."
...This is done by using gradient descent from a white noise image to minimise the mean-squared distance between the entries of the Gram matrices from the original image and the Gram matrices of the image to be generated [10, 25]....
[...]
...This general approach has been used before in the context of texture synthesis [12, 25, 10] and to improve the understanding of deep image representations [27, 24]....
[...]
4,333 citations
Cites methods from "A Parametric Texture Model Based on..."
...These synthesis methods provide a powerful and efficient means of testing a model, and have the added benefit that the resulting images suggest improvements that might be made to the model [ 11 ]....
[...]
...In previous work, the idea of synthesizing images for subjective testing has been employed by the “synthesisby-analysis” methods of assessing statistical texture models, in which the model is used to generate a texture with statistics matching an original texture, and a human subject then judges the similarity of the two textures [8]‐[ 11 ]....
[...]
4,146 citations
Cites background from "A Parametric Texture Model Based on..."
..., there are more wavelet coefficients than input pixels, the additional frequency and orientation selectivity makes this representation preferable for tasks such as texture analysis and synthesis (Portilla and Simoncelli 2000) and image denoising (Portilla et al....
[...]
3,920 citations
Cites background or methods from "A Parametric Texture Model Based on..."
...• Our algorithm is a principled probabilistic framework for learning models of textures via codewords (or textons) [5, 16, 10]....
[...]
...Much can also be learnt from studies for classifying different textures and materials [10, 5, 16]....
[...]
References
20,028 citations
18,761 citations
"A Parametric Texture Model Based on..." refers background or methods in this paper
...A number of authors have developed Markov texture models, along with tools for characterizing and sampling from such models (e.g. Hassner and Sklansky, 1980; Cross and Jain, 1983; Geman and Geman, 1984; Derin and Elliott, 1987)....
[...]
...Furthermore, sampling from this density is non-trivial, and typically requires computationally demanding algorithms such as the Gibbs sampler (Geman and Geman, 1984; Zhu et al., 1996), although recent work by Zhu et al....
[...]
...Furthermore, sampling from this density is non-trivial, and typically requires computationally demanding algorithms such as the Gibbs sampler (Geman and Geman, 1984; Zhu et al., 1996), although recent work by Zhu et al. on Monte Carlo Markov Chain methods has reduced these costs significantly (Zhu…...
[...]
12,099 citations
"A Parametric Texture Model Based on..." refers background in this paper
...A mathematically attractive choice is the density with maximum entropy that satisfies the set of constraints (Jaynes, 1957)....
[...]
8,588 citations
"A Parametric Texture Model Based on..." refers background in this paper
...An orthonormal wavelet representation (e.g., Daubechies, 1988; Mallat, 1989) suffers from a lack of translation-invariance, which is likely to cause artifacts in an application like texture synthesis (Simoncelli et al., 1992)....
[...]
3,077 citations
"A Parametric Texture Model Based on..." refers background in this paper
...In addition, recent studies of properties of natural images indicate that such decompositions can make accessible higher-order statistical regularities (e.g., Field, 1987; Watson, 1987; Daugman, 1988; Zetzsche et al., 1993; Simoncelli, 1997)....
[...]
...The set of all possible images is vast, and yet only a small fraction of these are likely to be encountered in a natural setting (Kersten, 1987; Field, 1987; Daugman, 1989; Ruderman and Bialek, 1994)....
[...]