I have finished implementation of some traditional texture synthesis algorithms: pixel-based [EL99] and patch-based [EF01]. The first one, as well known is quite slow. I tested some perspective texture samples with these algorithms, as shown in Fig 1 and Fig 2. It is obvious that the textures of different scales are mixed together. This is just a shortcoming of traditional algorithms. I have ne...

Dynamic textures are representations of such textured surfaces that exhibit certain stationarity properties in time. These include sea-waves, smoke, foliage, whirlwind, dense crowds, and traffic scenes. We address the problem of dynamic color texture synthesis which is a natural extending of the state-of-art Linear Dynamic System to the YUV color space by analyzing the intrinsic relationship be...

The synthesis of many textures can be simplified if they are first decomposed into simpler subtextures. Such bootstrap procedure allows to first consider a ‘label texture’, that captures the layout of the subtextures, after which the subtextures can be filled in. A companion paper focuses on this latter aspect. This paper describes an approach to arrive at the label texture. Pairwise pixel simi...

Data hiding techniques onto images provide tools for protecting copyright or sending secret messages, and they are currently utilized as a simple input device of a cell phone by detecting a data embedded in an image with an equipped digital camera. This paper presents a method of synthesizing texture images for embedding arbitrary data by utilizing the smart techniques of generating repetitive ...

We propose a recurrent variational auto-encoder for texture synthesis. A novel loss function, FLTBNK, is used for training the texture synthesizer. It is rotational and partially color invariant loss function. Unlike L2 loss, FLTBNK explicitly models the correlation of color intensity between pixels. Our texture synthesizer 1 generates neighboring tiles to expand a sample texture and is evaluat...

Partition of unity parametrics (PUPs) are a recent framework designed for geometric modeling. We propose employing PUPs for procedural texture synthesis, taking advantage of the framework’s guarantees of high continuity and local support. Using PUPs to interpolate among data values distributed through the plane, the problem of texture synthesis can be approached from the perspective of point pl...

Considerable evidence suggests that a viewer’s perception of the 3D shape of a polygonally-defined object can be significantly affected (either masked or enhanced) by the presence of a surface texture pattern. However, investigations into the specific mechanisms of texture’s effect on shape perception are still ongoing and the question of how to design and apply a texture pattern to a surface i...

Automatic reconstruction of archeological broken objects is an invaluable tool for restoration purposes and personnel. In this paper, we assume that broken pieces have similar characteristics on their common boundaries, when they are correctly combined. In this paper we work in a framework for the full reconstruction of the original objects using texture and surface design information on the sh...

In this paper a novel algorithm for sound texture synthesis is presented. The goal of this algorithm is to produce new examples of a given sampled texture, the synthesized textures being of any desired duration. The algorithm is based on a montage approach to synthesis in that the synthesized texture is made up of pieces of the original sample concatenated together in a new sequence. This monta...

The visual richness of computer graphics applications is frequently limited by the difficulty of obtaining high-quality, detailed 3D models. This paper proposes a method for realistically transferring details (specifically, displacement maps) from existing high-quality 3D models to simple shapes that may be created with easy-to-learn modeling tools. Our key insight is to use metric learning to ...