TU Darmstadt / ULB / TUbiblio

Hybrid Texture Synthesis

Nealen, Andrew (2003)
Hybrid Texture Synthesis.
Technische Universität Darmstadt
Diplom- oder Magisterarbeit, Bibliographie

Kurzbeschreibung (Abstract)

Patch-based texture synthesis algorithms produce reasonable results for a wide variety of texture classes. They preserve global structure, but often introduce unwanted visual artifacts along patch boundaries. Pixel-based synthesis algorithms, on the other hand, tend to blur out small objects while maintaining a consistent texture impression, which in return doesn't necessarily resemble the input texture. In this thesis, we propose an adaptive and hybrid algorithm. Our algorithm adaptively splits patches so as to use as large as possible patches while staying within a user-defined error tolerance for the mismatch in the overlap region. Using large patches improves the reproduction of global structure. The remaining errors in the overlap regions are eliminated using pixel-based re-synthesis. We introduce an optimized ordering for the re-synthesis of these erroneous pixels using morphological operators, which ensures that every pixel has enough valid (i.e., error-free) neighboring pixels. Examples and comparisons with existing techniques demonstrate that our approach improves over previous texture synthesis algorithms, especially for textures with well-visible, possibly anisotropic structure, such as natural stone wall or scales. Additionally, we extend the basic algorithm by an augmented patch-overlap error-metric based on frequency and feature distance. And finally, we enhance the speed of the pixel synthesis stage with hardly any visual drawback and intuitive user-controllable trade-off parameters.

Typ des Eintrags: Diplom- oder Magisterarbeit
Erschienen: 2003
Autor(en): Nealen, Andrew
Art des Eintrags: Bibliographie
Titel: Hybrid Texture Synthesis
Sprache: Deutsch
Publikationsjahr: 2003
Kurzbeschreibung (Abstract):

Patch-based texture synthesis algorithms produce reasonable results for a wide variety of texture classes. They preserve global structure, but often introduce unwanted visual artifacts along patch boundaries. Pixel-based synthesis algorithms, on the other hand, tend to blur out small objects while maintaining a consistent texture impression, which in return doesn't necessarily resemble the input texture. In this thesis, we propose an adaptive and hybrid algorithm. Our algorithm adaptively splits patches so as to use as large as possible patches while staying within a user-defined error tolerance for the mismatch in the overlap region. Using large patches improves the reproduction of global structure. The remaining errors in the overlap regions are eliminated using pixel-based re-synthesis. We introduce an optimized ordering for the re-synthesis of these erroneous pixels using morphological operators, which ensures that every pixel has enough valid (i.e., error-free) neighboring pixels. Examples and comparisons with existing techniques demonstrate that our approach improves over previous texture synthesis algorithms, especially for textures with well-visible, possibly anisotropic structure, such as natural stone wall or scales. Additionally, we extend the basic algorithm by an augmented patch-overlap error-metric based on frequency and feature distance. And finally, we enhance the speed of the pixel synthesis stage with hardly any visual drawback and intuitive user-controllable trade-off parameters.

Freie Schlagworte: Computer vision, Color image processing, Texture synthesis, Feature measurement
Zusätzliche Informationen:

69 S.

Fachbereich(e)/-gebiet(e): 20 Fachbereich Informatik
20 Fachbereich Informatik > Graphisch-Interaktive Systeme
Hinterlegungsdatum: 16 Apr 2018 09:04
Letzte Änderung: 18 Dez 2019 08:16
PPN:
Export:
Suche nach Titel in: TUfind oder in Google
Frage zum Eintrag Frage zum Eintrag

Optionen (nur für Redakteure)
Redaktionelle Details anzeigen Redaktionelle Details anzeigen