A Compound Moving Average Bidirectional Texture Function Model

@inproceedings{Haindl2016ACM,
  title={A Compound Moving Average Bidirectional Texture Function Model},
  author={Michal Haindl and Michal Havl{\'i}cek},
  booktitle={MISSI},
  year={2016}
}
This paper describes a simple novel compound random field model capable of realistic modelling the most advanced recent representation of visual properties of surface materials—the bidirectional texture function. The presented compound random field model combines a non-parametric control random field with local multispectral models for single regions and thus allows to avoid demanding iterative methods for both parameters estimation and the compound random field synthesis. The local texture… 
4 Citations

BTF Compound Texture Model with Non- Parametric Control Field

A novel multidimensional statistical model for realistic modeling, enlargement, editing, and compression of the recent state-of-the-art bidirectional texture function (BTF) textural representation which allows reaching huge compression ratio incomparable with any standard image compression method.

Appearance Bending: A Perceptual Editing Paradigm for Data-Driven Material Models

This work introduces appearance bending, a set of image-based manipulation operators that implement recent insights from perceptual studies, and exploits a link between certain perceived visual properties of a material, and specific bands in its spectrum of spatial frequencies or octaves of a wavelet decomposition.

Appearance Bending

This work introduces appearance bending, a set of image-based manipulation operators that implement recent insights from perceptual studies, and exploits a link between certain perceived visual properties of a material, and specific bands in its spectrum of spatial frequencies or octaves of a wavelet decomposition.

Model Based Texture Features

Model-based texture analysis attempts to represent an image texture using the stochastic model and generative image model to help improve the quality of texture analysis results.

References

SHOWING 1-10 OF 24 REFERENCES

A Compound MRF Texture Model

The proposed compound Markov random field model combines a non-parametric control random field with analytically solvable wide sense Markov representation for single regions and thus allows to avoid demanding Markov Chain Monte Carlo methods for both parameters estimation and the compound random field synthesis.

A Plausible Texture Enlargement and Editing Compound Markovian Model

The presented compound Markov random field model combines a non-parametric control random field with analytically solvable wide-sense Markov representation for single regions and thus allows very efficient non-iterative parameters estimation as well as the compound random field synthesis.

Potts compound Markovian texture model

This paper describes a novel multispectral parametric compound Markov random field model for texture synthesis that connects a parametric control random field represented by a hierarchical Potts Markovrandom field model with analytically solvable wide-sense Markovian representation for single regions.

A Moving Average Bidirectional Texture Function Model

This work presents a novel BTF model based on a set of underlying mono-spectral two-dimensional (2D) moving average factors that enables very high BTF space compression ratio, unlimited texture enlargement, and reconstruction of missing unmeasured parts of the B TF space.

BTF Potts compound texture model

This paper introduces a method for modeling mosaic-like textures using a multispectral parametric Bidirectional Texture Function (BTF) compound Markov random field model (CMRF), which generally surpasses the outputs of the previously published simpler non-compound BTF-MRF models.

An efficient two dimensional moving average model for texture analysis and synthesis

A linear 2D moving average model which serves a dual purpose in the analysis and synthesis of stochastic texture is presented. This model is based on the assumption that a stochastic texture is

Extreme Compression and Modeling of Bidirectional Texture Function

  • M. HaindlJ. Filip
  • Computer Science
    IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2007
A novel, fast probabilistic model-based algorithm for realistic BTF modeling allowing an extreme compression with the possibility of a fast hardware implementation and its ultimate aim is to create a visual impression of the same material without a pixelwise correspondence to the original measurements.

Bidirectional Texture Function Simultaneous Autoregressive Model

This novel Markovian BTF model based on a set of underlying simultaneous autoregressive models (SAR) combines several multispectral band limited spatial factors and range map sub-models to produce the required BTF texture space.

A Multiresolution Causal Colour Texture Model

An efficient recursive algorithm for realistic colour texture synthesis is proposed that replaces a large neighbourhood CAR model with a set of several simpler CAR models which are easy to synthesize and wider application area of these multigrid models capable of reproducing realistic textures for enhancing realism in texture application areas.

A Roller - Fast Sampling-Based Texture Synthesis Algorithm

The novel texture synthesis method, which the authors call the roller, is based on the overlapping tiling and subsequent minimum error boundary cut and an optimal double toroidal patch is seamlessly repeated during the synthesis step.