| Textures can describe a wide variety of natural phenomena with random variations over repeating patterns. Examples of textures include images, motions, and surface geometry. Since reproducing the realism of the physical world is a major goal for computer graphics, textures are important for rendering synthetic images and animations. However, because textures are so diverse it is difficult to describe and reproduce them under a common framework.; In this thesis, we present new methods for synthesizing textures. The first part of the thesis is concerned with a basic algorithm for reproducing image textures. The algorithm is easy to use and requires only a sample texture as input. It generates textures with perceived quality equal to or better than those produced by previous techniques, but runs orders of magnitude faster. The algorithm is derived from Markov Random Field texture models and generates textures through a deterministic searching process. Because of the use of this deterministic searching, our algorithm can avoid the computational demand of probability sampling and can be directly accelerated by a point searching algorithm such as tree-structured vector quantization.; The second part of the thesis concerns various extensions and applications of our texture synthesis algorithm. The applications include constrained synthesis, in which artifacts in files or photographs are removed by replacing them with synthesized texture backgrounds; motion texture synthesis, in which texture synthesis is applied to generate repetitive motion textures such as 3D temporal textures and 1D articulated motion signals; surface texture synthesis, in which textures are grown directly over manifold surfaces; multiple-source texture synthesis, in which new textures are generated from multiple sources; and order-independent texture synthesis, in which a new texture can be generated on demand in an arbitrary traversal order without producing inconsistent results.; We conclude this thesis by analyzing the algorithm behavior and discussing future work. |
