Texture Optimization for Example-based Synthesis

energy plot    Keyboard flowing like smoke


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.


Related publication:

Texture Optimization for Example-based Synthesis

Vivek Kwatra , Irfan Essa , Aaron Bobick and Nipun Kwatra
To appear in Proc. ACM Transactions on Graphics, SIGGRAPH 2005
Paper 5.8 MB | SIGGRAPH Video 139 MB  | BibTex | SIGGRAPH Talk (ZIP: with movies 53MB) | SIGGRAPH Talk (PPT: no movies 3.2MB)

Poster presented at Symposium on Computational Photography and Video (SCPV'05)


Results:

Image Results
Energy Plot ; Progression ( slow | fast | texture only)
Pebbles texture progression ( 10fps | 30fps )