Informationen für

Logo VISUS

Interactive Parameter Retrieval of Two-Tone Procedural Textures

Eurographics Symposium on Rendering (EGSR 2014)

Lena Gieseke1,2, Sebastian Koch1, Jens-Uwe Hahn2, Martin Fuchs1

1 University of Stuttgart, Germany
2 Stuttgart Media University, Germany


Teaser

Principal Component Analysis reveals the constituent colors of a two-tone image and a corresponding blend map. By identifying the most similar image from a database of images generated by a procedural texture model according to a texture descriptor, we can retrieve structural parameters. Together with the colors, they produce an image closely matching the input.

Abstract

The choice of parameters for procedural textures to achieve a desired appearance poses a challenging problem even for experienced artists. We propose a method to automatically determine such parameters to reproduce the appearance of input images. Addressing two-tone textures, we separate the estimation of color and structure information and interpret the problem as image retrieval task from the space of procedural outputs.
Applying a perceptually motivated image metric based on a texture descriptor enables us to precompute a comprehensive collection of possible parameter sets and yet achieve interactive retrieval performance.
Our method supports a large variety of procedural texture models with a unified approach.


Publication

2014

Artikel

Interactive Parameter Retrieval For Two-Tone Procedural Textures
Gieseke, Lena; Koch, Sebastian; Hahn, Jens-Uwe; Fuchs, Martin: Interactive Parameter Retrieval For Two-Tone Procedural Textures.
Computer Graphics Forum 33 (4), S. 71–79 (2014).

Supplemental Material

  • Texture Models
    - Exemplary source code
    - Detailed description of parameter counts, value ranges, sampling densities and exemplary visualizations

Acknowledgments

This work was partially funded by the graduate program Digital Media, granted by the state Baden-Württemberg, Germany.