Probabilistic Texture Synthesis

A Moving Average Bidirectional Texture Function Model


Abstract: 
The Bidirectional Texture Function (BTF) is the recent most advanced representation of visual properties of surface materials. It specifies their appearance due to varying spatial, illumination, and viewing conditions. Corresponding enormous BTF measurements require a mathematical representation allowing extreme compression but simultaneously preserving its high visual fidelity. We present a novel BTF model based on a set of underlying mono-spectral two-dimensional (2D) moving average factors. A mono-spectral moving average model assumes that a stochastic mono-spectral texture is produced by convolving an uncorrelated 2D random field with a 2D filter which completely characterizes the texture. The BTF model combines several multi-spectral band limited spatial factors, subsequently factorized into a set of mono-spectral moving average representations, and range map to produce the required BTF texture space. This enables very high BTF space compression ratio, unlimited texture enlargement, and reconstruction of missing unmeasured parts of the BTF space.

Bidirectional Texture Function Three Dimensional Pseudo Gaussian Markov Random Field Model


Abstract: 
The Bidirectional Texture Function (BTF) is the recent most advanced representation of material surface visual properties. BTF specifies the changes of its visual appearance due to varying illumination and viewing angles. Such a function might be represented by thousands of images of given material surface. Original data cannot be used due to its size and some compression is necessary. This paper presents a novel probabilistic model for BTF textures. The method combines synthesized smooth texture and corresponding range map to produce the required BTF texture. Proposed scheme enables very high BTF texture compression ratio and may be used to reconstruct BTF space as well.

Bidirectional Texture Function Simultaneous Autoregressive Model


Abstract: 
Abstract. The Bidirectional Texture Function (BTF) is the recent most advanced representation of visual properties of surface materials. It specifies their altering appearance due to varying illumination and viewing conditions. Corresponding huge BTF measurements require a mathematical representation allowing simultaneously extremal compression as well as high visual fidelity. We present a novel Markovian BTF model based on a set of underlying simultaneous autoregressive models (SAR). This complex but efficient BTF-SAR model combines several multispectral band limited spatial factors and range map sub-models to produce the required BTF texture space. The BTF-SAR model enables very high BTF space compression ratio, texture enlargement, and reconstruction of missing unmeasured parts of the BTF space.

Texture Modelling by Discrete Distribution Mixtures


Abstract: 
This texture modelling aaproach is based on discrete distribution mixtures. Unlike some alternative approaches the statistical properties of textures are modelled by a discrete distribution mixture of product components. The univariate distributions in the products are represented in full generality by vectors of probabilities without any constraints. The texture analysis is made in the original quantized spectral level coding. An efficient texture synthesis is based on easy computation of arbitrary conditional distributions from the model. Several successful colour texture applications of the method demonstrate the advantages and but also weak points of the presented approach.

Texture Synthesis Using Single-Scale / Multiple-Scale Markov Random Field Models


Abstract: 
This fast multigrid colour texture synthesis algorithm starts with spectral factorization of an input colour texture image using the Karhunen-Loeve expansion. Single orthogonal monospectral components are further decomposed into a multi-resolution grid and each resolution factors are independently modeled by their dedicated Markov random field model. Finally single synthesized monospectral single-resolution texture factorss are collapsed into the fine resolution images and using the inverse Karhunen-Loeve transformation we obtain the required colour texture.