A Parametric Texture Model Based on Joint Statistics of Complex Wavelet Coefficients

@article{Portilla2004APT,
  title={A Parametric Texture Model Based on Joint Statistics of Complex Wavelet Coefficients},
  author={Javier Portilla and Eero P. Simoncelli},
  journal={International Journal of Computer Vision},
  year={2004},
  volume={40},
  pages={49-70}
}
We present a universal statistical model for texture images in the context of an overcomplete complex wavelet transform. The model is parameterized by a set of statistics computed on pairs of coefficients corresponding to basis functions at adjacent spatial locations, orientations, and scales. We develop an efficient algorithm for synthesizing random images subject to these constraints, by iteratively projecting onto the set of images satisfying each constraint, and we use this to test the… Expand
Texture synthesis via projection onto multiscale, multilayer statistics
TLDR
The power of the new model for texture synthesis based on a multiscale, multi-layer feature extractor based on ReLU wavelet coefficients is demonstrated by generating samples of high quality textures and providing insights into deep representations for texture images. Expand
A Generative Model of Natural Texture Surrogates
TLDR
The parametric texture algorithm is applied to image patches of 64X64 pixels in a large database of natural images such that each image patch is described by 655 texture parameters which specify certain statistics, such as variances and covariances of wavelet coefficients or coefficient magnitudes within that patch. Expand
A Conditional Multiscale Locally Gaussian Texture Synthesis Algorithm
TLDR
This work model texture self-similarity with conditional Gaussian distributions in the patch space in order to extend the use of stitching techniques and shows the effectiveness of the proposed technique for a wide range of textures. Expand
A Generative Model of Textures Using Hierarchical Probabilistic Principal Component Analysis
TLDR
A contracted texture model is proposed which provides a dimension reduction for the Portillas' feature and it is demonstrated how well the textures can be synthesized from the contracted texture representations. Expand
Joint linear-circular stochastic models for texture classification
TLDR
Both linear and circular stochastic models in the context of texture discrimination aimed at representing the magnitudes and orientations obtained by a complex wavelet decomposition, such as the steerable pyramid are investigated. Expand
Multiscale Exemplar Based Texture Synthesis by Locally Gaussian Models
TLDR
A multiscale approach able to combine advantages of both strategies and avoid some of their drawbacks is proposed, which allows to fix a patch size fairly independent of the texture. Expand
Conditional Gaussian Models for Texture Synthesis
TLDR
The experiments here show that the conditional model reproduces well periodic and pseudo-periodic textures without requiring the use of any stitching technique and put also in evidence the importance of the right choice for the patch size. Expand
A Generative Model of Textures Using Hierarchical Probabilistic Principal Co m ponent Analysis ( Regular Research Paper )
Modeling of textures in natural images is an important task to make a microscopic model of natural images. Portilla and Simoncelli proposed a generative texture model, which is based on the mechanismExpand
Locally Gaussian exemplar based texture synthesis
TLDR
This communication proposes to involve a locally Gaussian texture model in the patch space, which permits to synthesize textures that are everywhere different from the original but with better quality than the purely statistical methods. Expand
On the use of marginal statistics of subband images
  • J. Gluckman
  • Computer Science
  • Proceedings Ninth IEEE International Conference on Computer Vision
  • 2003
TLDR
The results suggest the need for either employing a large and diverse filter bank or incorporating joint statistics in order to represent a large class of visual patterns. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 94 REFERENCES
Texture modeling and synthesis using joint statistics of complex wavelet coefficients
TLDR
A statistical characterization of texture images in the context of an overcomplete complex wavelet transform is presented, and it is shown that many important structural elements in textures can be captured through joint second order statistics of the coeÆcient magnitudes. Expand
Texture characterization via joint statistics of wavelet coefficient magnitudes
  • Eero P. Simoncelli, J. Portilla
  • Computer Science, Mathematics
  • Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269)
  • 1998
TLDR
An efficient algorithm for sampling from an implicit probability density conforming to these statistics is developed, and its effectiveness in synthesizing artificial and natural texture images is demonstrated. Expand
Independent component analysis of textures
  • R. Manduchi, J. Portilla
  • Computer Science, Mathematics
  • Proceedings of the Seventh IEEE International Conference on Computer Vision
  • 1999
TLDR
This work proposes a technique, based on independent component analysis, for choosing the set of filters that yield the most informative marginals, meaning that the product over the marginals most closely approximates the joint probability density function of the filter outputs. Expand
A unified texture model based on a 2-D Wold-like decomposition
TLDR
A unified texture model that is applicable to a wide variety of texture types found in natural images is presented and results show that the deterministic components should be parameterized separately from the purely indeterministic component. Expand
The use of Markov Random Fields as models of texture
Abstract We propose Markov Random Fields (MRFs) as probabilistic models of digital image texture where a textured region is viewed as a finite sample of a two-dimensional random process describableExpand
Scale Mixtures of Gaussians and the Statistics of Natural Images
The statistics of photographic images, when represented using multiscale (wavelet) bases, exhibit two striking types of non-Gaussian behavior. First, the marginal densities of the coefficients haveExpand
Localized texture processing in vision: analysis and synthesis in the Gaborian space
  • M. Porat, Y. Zeevi
  • Mathematics, Medicine
  • IEEE Transactions on Biomedical Engineering
  • 1989
TLDR
A method for texture discrimination and image segmentation using local features based on the Gabor approach is introduced and the results show the insensitivity of the discrimination to relatively high noise levels, comparable to the performances of the human observer. Expand
Markov Random Field Texture Models
  • G. R. Cross, Anil K. Jain
  • Computer Science, Mathematics
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 1983
TLDR
The power of the binomial model to produce blurry, sharp, line-like, and blob-like textures is demonstrated and the synthetic microtextures closely resembled their real counterparts, while the regular and inhomogeneous textures did not. Expand
Visual Discrimination of Stochastic Texture Fields
TLDR
It is demonstrated, for the stochastic models investigated, that humans cannot effortlessly discriminate between pairs of spatially correlated texture fields with differing third-order probability densities when their lower order densities are pairwise equal. Expand
Image texture synthesis-by-analysis using moving-average models
A synthesis-by-analysis model for texture replication or simulation is presented. This model can closely replicate a given textured image or produce another image that although distinct from theExpand
...
1
2
3
4
5
...