Texture synthesis aims to define and reproduce discriminating image features. These features are used to associate with and differentiate between two textures. Often texture is composed of a pattern with an element of randomness in each feature’s appearance, position and orientation. The goal is to imitate the sample texture in such a way that sample and synthesised texture are perceived to be ...

Measured material representations like Bidirectional Texture Functions or Reflectance Fields offer very realistic appearance but the user is currently not capable of changing this appearance in an effective and intuitive way. Such editing operations would require a low-dimensional but expressive model for appearance that exposes only a small set of intuitively editable parameters (1D-sliders, 2...

Textures have been used in various applications, such as carpet quality control, region recognition in satellite images, and body painting control in the vehicle industry. This paper studies texture synthesis. We survey the algorithms for synthesizing textures that have proposed over the past two decades. A variety of algorithms associated with synthesized textures are given. The goal is to fur...

Many interesting real-world textures are inhomogeneous and/or anisotropic. An inhomogeneous texture is one where various visual properties exhibit significant changes across the texture’s spatial domain. Examples include perceptible changes in surface color, lighting, local texture pattern and/or its apparent scale, and weathering effects, which may vary abruptly, or in a continuous fashion. An...

We propose using the Deep Recurrent Attentive Writer (DRAW) network [1] for texture synthesis. We managed to train and deploy DRAW tensorflow implementation. Simple texture synthesis experiments were evaluated to verify the idea validity. Figure 1 shows a sample result for a tilted chess board texture. The generated tiles not only capture the correct texture but also aligns smoothly with the ce...

While there is a vast amount of literature considering PDE based inpainting and inpainting by texture synthesis, only a few publications are concerned with combination of both approaches. We present a novel algorithm which combines both approaches and treats each distinct region of the image separately. Thus we are naturally lead to include a segmentation pass as a new feature. This way the cor...

New advances in image based texture synthesis techniques allow the generation of arbitrarily sized textures based on a small sample. The generated textures are perceived as very similar to the given sample. One main drawback of these techniques, however, is that the synthesized result cannot be locally controlled, that is, we are able to synthesize a larger version of the sample but without muc...