We present a method for binary texture synthesis based on thresholds of Gaussian random fields. The method enables us to reproduce the average value and correlation function of the observed texture. The method is comparatively simple, and it seems to be effective for a wide class of random binary textures. In the paper we discuss properties of the method and illustrate its performance in the st...

Motivated by the desire to quantify the output of various texture synthesis algorithms, our method uses classical statistical measures to test the quality of outputs for five different categories of texture. We test our approach on three texture synthesis algorithms and present our results here. Of the three different algorithms tested, one is pixel based, the second a patch based approach, and...

Vector field visualization generates an image to convey the information existing in the data. We use Markov Random Field texture synthesis methods to generate the visualization from a set of example textures. The examples textures are chosen according to the vector data for each pixel of the output. This leads to dense visualizations with arbitrary example textures.

This paper is two-fold. On the one hand, we present a system using qualitative spatial reasoning to help a user choose parts of an image that form interesting objects. The system then allows the user to cut these parts as if unwanted in the original image. On the other hand, we propose a modification of existing texture synthesis methods to create texture in the holes left by the cutting of pre...

Generative adversarial networks (GANs) [7] are a recent approach to train generative models of data, which have been shown to work particularly well on image data. In the current paper we introduce a new model for texture synthesis based on GAN learning. By extending the input noise distribution space from a single vector to a whole spatial tensor, we create an architecture with properties well...

While texture synthesis has been well-studied in recent years, real-time techniques remain elusive. To help facilitate real-time texture synthesis, we divide the task of texture synthesis into two phases: a relatively slow analysis phase, and a real-time synthesis phase. Any particular texture need only be analyzed once, and then an unlimited amount of texture may be synthesized in real-time. O...

An algorithm for synthesizing color textures from a small set of parameters is presented in this paper. The synthesis algorithm is based on the 2-D moving average model, and realistic textures resembling many real textures can be synthesized using this algorithm. A maximum likelihood estimation algorithm to estimate parameters from a sample texture is also presented. Using the estimated paramet...

Transferring surface properties such as color texture from one 3D mesh to another is a well-known problem, which has become increasingly important as the demand for textured models in games and films has grown. We propose a mesh-based analogy of the PatchMatch [Barnes et al. 2009] algorithm, which we call “MeshMatch,” and a non-parametric multi-resolution approach to surface texture transfer ba...

Image quilting is a texture synthesis technique to create a large texture by wrapping around patches of a small texture in a way that the repetition of small texture is not noticeable. The basic algorithm is to randomly select small patches in a given texture. These patches are then positioned in a large texture to be synthesized and blended across boundaries to remove the appearance of boundar...

We propose a texture analysis method based on Rényi’s entropies. The method aims at identifying texels in regular textures by searching for the smallest window through which the minimum number of different visual patterns is observed when moving the window over a given texture. The experimental results show that any of Rényi’s entropies can be used for texel identification. However, the second ...