Paper in ACM SIGGRAPH 2005 on “Texture Optimization for Example-based Synthesis”

Citation

V. Kwatra, I. Essa, A. Bobick, N. Kwatra: Texture Optimization for Example-based Synthesis. In: ACM SIGGRAPH Proceedings of Annual Conference on Computer graphics and interactive techniques, vol. 24, no. 3, pp. 795–802, 2005.

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 concerning a given input sample. This allows us to formulate the synthesis problem as the 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 the 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.

Links

BibTeX (Download)

@article{2005-Kwatra-TOES,
title = {Texture Optimization for Example-based Synthesis},
author = {V. Kwatra and I. Essa and A. Bobick and N. Kwatra},
url = {https://dl.acm.org/doi/10.1145/1186822.1073263
https://www.cc.gatech.edu/gvu/perception/projects/textureoptimization/
https://youtu.be/Ys_U46-FeEM
http://www.cc.gatech.edu/gvu/perception/projects/textureoptimization/TextureOptimization_DVD.mov
http://www.cc.gatech.edu/gvu/perception/projects/textureoptimization/TO-sig05.ppt
http://www.cc.gatech.edu/gvu/perception/projects/textureoptimization/TO-final.pdf
},
doi = {10.1145/1073204.1073263},
year  = {2005},
date = {2005-08-01},
urldate = {2005-08-01},
journal = {ACM SIGGRAPH Proceedings of Annual Conference on Computer graphics and interactive techniques},
volume = {24},
number = {3},
pages = {795--802},
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 concerning a given input sample. This allows us to formulate the synthesis problem as the 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 the 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.},
keywords = {ACM, computational video, computer animation, computer graphics, computer vision, SIGGRAPH},
pubstate = {published},
tppubtype = {article}
}