#### DMCA

## Model-based estimation of texels and placement grids for fast realistic texture synthesis. Texture 2003, The 3rd international workshop on texture analysis and synthesis (2003)

Citations: | 1 - 0 self |

### Citations

1234 | On the statistical analysis of dirty pictures
- Besag
- 1986
(Show Context)
Citation Context ...re synthesis are based on Markov random field (MRF) models and can be roughly divided into two groups, namely, model based probabilistic synthesis and non-parametric sampling. The model based methods =-=[1]-=-, [3], [4], [7]–[9], [17] identify first a particular MRF model of a given training texture specified usually by a joint Gibbs probability distribution (GPD) of image signals, and generate textures us... |

996 | Texture synthesis by non-parametric sampling
- Efros, Leung
- 1999
(Show Context)
Citation Context ... image generation are computationally intensive processes, these approaches are less feasible for synthesising large-size textures. Much faster synthesis is obtained with non-parametric sampling [5], =-=[6]-=-, [12]. Also assuming Markovianity of the texture, these techniques treat the training image as a source of random signal samples related to the underlying marginal GPDs. They synthesise new textures ... |

822 |
Textures: A Photographic Album for Artists and Designers
- Brodatz
- 1966
(Show Context)
Citation Context ...(ξ,η)∈AsPartial Energy (E ξ,η ) 80 70 60 50 40 D3 D4 D6 D9 D29 D34 D57 D101 flower0002 food0002 grass0002 metal0003 Fig. 1. Training textures (128 × 128) taken or cut from the digitised Brodatz album =-=[2]-=- and the MIT VisTex texture database [13]. −30 −30 −30 −20 −20 −20 −10 −10 −10 0 η 10 20 20 10 0 ξ 0 η 10 20 30 30 30 η 30 20 10 0 −10 −20 −30 D4-MBIM −30 −20 −10 0 10 20 30 ξ D4: |A ∗ |=38 Partial En... |

690 | Image quilting for texture synthesis and transfer
- Efros, Freeman
- 2001
(Show Context)
Citation Context ...d the image generation are computationally intensive processes, these approaches are less feasible for synthesising large-size textures. Much faster synthesis is obtained with non-parametric sampling =-=[5]-=-, [6], [12]. Also assuming Markovianity of the texture, these techniques treat the training image as a source of random signal samples related to the underlying marginal GPDs. They synthesise new text... |

348 |
Markov random fields texture models
- Cross, Jain
- 1983
(Show Context)
Citation Context ...is are based on Markov random field (MRF) models and can be roughly divided into two groups, namely, model based probabilistic synthesis and non-parametric sampling. The model based methods [1], [3], =-=[4]-=-, [7]–[9], [17] identify first a particular MRF model of a given training texture specified usually by a joint Gibbs probability distribution (GPD) of image signals, and generate textures using Markov... |

58 |
Two-dimensional discrete Gaussian Markov random field models for image processing
- Chellappa
- 1985
(Show Context)
Citation Context ...nthesis are based on Markov random field (MRF) models and can be roughly divided into two groups, namely, model based probabilistic synthesis and non-parametric sampling. The model based methods [1], =-=[3]-=-, [4], [7]–[9], [17] identify first a particular MRF model of a given training texture specified usually by a joint Gibbs probability distribution (GPD) of image signals, and generate textures using M... |

37 |
Image Textures and Gibbs Random Fields
- Gimel’farb
- 1999
(Show Context)
Citation Context ...sed on Markov random field (MRF) models and can be roughly divided into two groups, namely, model based probabilistic synthesis and non-parametric sampling. The model based methods [1], [3], [4], [7]–=-=[9]-=-, [17] identify first a particular MRF model of a given training texture specified usually by a joint Gibbs probability distribution (GPD) of image signals, and generate textures using Markov Chain Mo... |

7 |
Non-Markov Gibbs texture model with multiple pairwise pixel interactions
- Gimel’farb
- 1996
(Show Context)
Citation Context ...e based on Markov random field (MRF) models and can be roughly divided into two groups, namely, model based probabilistic synthesis and non-parametric sampling. The model based methods [1], [3], [4], =-=[7]-=-–[9], [17] identify first a particular MRF model of a given training texture specified usually by a joint Gibbs probability distribution (GPD) of image signals, and generate textures using Markov Chai... |

3 | Texture modeling with multiple pairwise pixel interactions - Gimel'farb - 1996 |

1 |
Fast synthesis of large-size textures using bunch sampling
- Gimel’farb, Zhou
- 2002
(Show Context)
Citation Context ...e is no theoretically justified technique to select the proper size of the samples for various textures. This paper details an alternative approach to fast texture synthesis, called bunch sampling in =-=[10]-=-, [16], that aims to bridge gaps between the model based synthesis and nonparametric sampling by combining the strength of the both approaches. The structural approach to texture analysis [11] conside... |