Texture synthesis is a well-established area, with many important applications in computer graphics and vision. However, despite their success, synthesis techniques are not used widely in practice because the creation of good exemplars remains challenging and extremely tedious. In this paper, we introduce an unsupervised method for analyzing texture content across multiple scales that automatically extracts good exemplars from natural images. Unlike existing methods, which require extensive manual tuning, our method is fully automatic. This allows the user to focus on using texture palettes derived from their own images, rather than on manual interactions dictated by the needs of an underlying algorithm. Most natural textures exhibit patterns at multiple scales that may vary according to the location (non-stationarity). To handle such textures many synthesis algorithms rely on an analysis of the input and a guidance of the synthesis. Our new analysis is based on a labeling of texture patterns that is both (i) multi-scale and (ii) unsupervised -- that is, patterns are labeled at multiple scales, and the scales and the number of labeled clusters are selected automatically. Our method works in two stages. The first builds a hierarchical extension of superpixels and the second labels the superpixels based on random walk in a graph of similarity between superpixels and a nonnegative matrix factorization. Our label-maps provide descriptors for pixels and regions that benefit state-of-the-art texture synthesis algorithms. We show several applications including guidance of non-stationary synthesis, content selection and texture painting. Our method is designed to treat large inputs and can scale to many megapixels. In addition to traditional exemplar inputs, our method can also handle natural images containing different textured regions.

Texture is an essential feature in modeling the appearance of objects and is instrumental in making virtual objects appear interesting and/or realistic. Unfortunately, obtaining textures is a labor intensive task requiring parameter tuning for procedural methods or careful photography and post-processing for natural images. Many texture synthesis techniques have been developed to generate textures of arbitrary spatial extent, but these techniques require the user to first produce an exemplar consisting solely of the desired texture. We present a fast method using diffusion manifolds to locate textures in unconstrained photographs, and extract exemplar tiles. The method requires the user to only specify a single point within the image containing the desired texture and the scale of the desired texture. The user may tune the result using simple interactions. The method is non-local, in the sense that the desired texture does not have to appear in a single contiguous region in the source image. This document is a summary of our work and system. A full account is available online.