GPU-based Multi-Resolution Image Analysis for Synthesis of Tileable Textures

Information

• Publication Type: Conference Paper
• Workgroup(s)/Project(s):
  • VRVis Competence Center
• Date: July 2012
• ISBN: 978-3-642-33190-9
• Series: Lecture Notes in Computer Science (LNCS) series
• Publisher: Springer-Verlag
• Organization: Symposium proceedings
• Location: Creta, Greece
• Lecturer: Gottfried Eibner
• ISSN: 0302-9743
• Booktitle: Proceedings Intern. Symposium on Visual Computing (ISVC 2012)
• Conference date: 16. July 2012 – 18. July 2012
• Pages: 479 – 488

Abstract

We propose a GPU-based algorithm for texture analysis and synthesis of nearly-regular patterns, in our case scanned textiles or similar manufactured surfaces. The method takes advantage of the highly parallel execution on the GPU to generate correlation maps from captured template images. In an analysis step a lattice encoding the periodicity of the texture is computed. This lattice is used to synthesize the smallest texture tile describing the underlying pattern. Compared to other approaches, our method analyzes and synthesizes a valid lattice model without any user interaction. It is robust against small distortions and fast compared to other, more general approaches.

Additional Files and Images

Weblinks

No further information available.

BibTeX

@inproceedings{Eibner-12,
  title =      " GPU-based Multi-Resolution Image Analysis for Synthesis of
               Tileable Textures",
  author =     "Gottfried Eibner and Anton Fuhrmann and Werner Purgathofer",
  year =       "2012",
  abstract =   "We propose a GPU-based algorithm for texture analysis and
               synthesis of nearly-regular patterns, in our case scanned
               textiles or similar manufactured surfaces. The method takes
               advantage of the highly parallel execution on the GPU to
               generate correlation maps from captured template images. In
               an analysis step a lattice encoding the periodicity of the
               texture is computed. This lattice is used to synthesize the
               smallest texture tile describing the underlying pattern.
               Compared to other approaches, our method analyzes and
               synthesizes a valid lattice model without any user
               interaction. It is robust against small distortions and fast
               compared to other, more general approaches. ",
  month =      jul,
  isbn =       "978-3-642-33190-9",
  series =     "Lecture Notes in Computer Science (LNCS) series",
  publisher =  "Springer-Verlag",
  organization = "Symposium proceedings",
  location =   "Creta, Greece",
  issn =       "0302-9743",
  booktitle =  "Proceedings Intern. Symposium on Visual Computing (ISVC
               2012)",
  pages =      "479--488",
  URL =        "https://www.cg.tuwien.ac.at/research/publications/2012/Eibner-12/",
}