Texture optimization for example-based synthesis

Abstract

We present a novel technique for texture synthesis using optimization. We define a Markov Random Field (MRF)-based similarity metric for measuring the quality of synthesized texture with respect to a given input sample. This allows us to formulate the synthesis problem as minimization of an energy function, which is optimized using an Expectation Maximization (EM)-like algorithm. In contrast to most example-based techniques that do region-growing, ours is a joint optimization approach that progressively refines the entire texture. Additionally, our approach is ideally suited to allow for controllable synthesis of textures. Specifically, we demonstrate controllability by animating image textures using flow fields. We allow for general two-dimensional flow fields that may dynamically change over time. Applications of this technique include dynamic texturing of fluid animations and texture-based flow visualization.

Repeatable texture sampling with interchangeable patches

“…Instead of performing the process once, patches can be placed iteratively over the output until desired quality is achieved [8,21]. However, sequential algorithms are not suitable for simultaneous synthesis of disjoint regions, because the space between them needs to be synthesised as well.…”

Optimal Patch Assignment for Statistically Constrained Texture Synthesis

“…Their success is however not guaranteed: when the input image contains constant or blurry regions, these can be indeed enlarged during the synthesis, creating "garbage regions" [8,1,23]. A more principled approach consists in synthesizing the output texture through the minimization of a patch-based dissimilarity texture energy [19,13]. These methods are able to obtain high quality results for both stochastic and structured textures.…”

Physically-Based Surface Texture Synthesis Using a Coupled Finite Element System

“…During the past decade, many example-based texture synthesis methods have been proposed, including parametric methods [12,19,6,7], non-parametric methods [13,14,20,27,28], optimization-based methods [15,10], and appearance-space texture synthesis [16]. In order to synthesize textures over surfaces based on a given texture example, parametric methods attempt to construct a parametric model of the texture.…”

“…( 15) where τ is the time step, and a n is the concentration at time t = nτ. Equation (14)(15) can be rewritten into a linear system in Equation (8).…”

“…Equation (14)(15) can be rewritten into a linear system in Equation (8). The mass matrix, the stiffness matrix and the force vector of Equation (14) are as follows, Similarly, the mass matrix, the stiffness matrix and the force vector of Equation (15) are as follows,…”