TU Darmstadt / ULB / TUbiblio

Steerable Random Fields

Roth, Stefan ; Black, Michael (2007)
Steerable Random Fields.
IEEE 11th International Conference on Computer Vision.
Konferenzveröffentlichung, Bibliographie

Kurzbeschreibung (Abstract)

In contrast to traditional Markov random field (MRF) models, we develop a Steerable Random Field (SRF) in which the field potentials are defined in terms of filter responses that are steered to the local image structure. In particular, we use the structure tensor to obtain derivative responses that are either aligned with, or orthogonal to, the predominant local image structure, and analyze the statistics of these steered filter responses in natural images. Clique potentials are defined over steered filter responses using a Gaussian scale mixture model and are learned from training data. The SRF model connects random field models with anisotropic regularization and provides a statistical motivation for the latter. We demonstrate that steering the random field to the local image structure improves image denoising and inpainting performance compared with traditional pairwise MRFs.

Typ des Eintrags: Konferenzveröffentlichung
Erschienen: 2007
Autor(en): Roth, Stefan ; Black, Michael
Art des Eintrags: Bibliographie
Titel: Steerable Random Fields
Sprache: Deutsch
Publikationsjahr: 2007
Verlag: IEEE Computer Society, Los Alamitos, Calif.
Veranstaltungstitel: IEEE 11th International Conference on Computer Vision
Kurzbeschreibung (Abstract):

In contrast to traditional Markov random field (MRF) models, we develop a Steerable Random Field (SRF) in which the field potentials are defined in terms of filter responses that are steered to the local image structure. In particular, we use the structure tensor to obtain derivative responses that are either aligned with, or orthogonal to, the predominant local image structure, and analyze the statistics of these steered filter responses in natural images. Clique potentials are defined over steered filter responses using a Gaussian scale mixture model and are learned from training data. The SRF model connects random field models with anisotropic regularization and provides a statistical motivation for the latter. We demonstrate that steering the random field to the local image structure improves image denoising and inpainting performance compared with traditional pairwise MRFs.

Freie Schlagworte: Forschungsgruppe Visual Inference (VINF), Computer vision, Image data models, Low level image processing
Fachbereich(e)/-gebiet(e): nicht bekannt
20 Fachbereich Informatik
20 Fachbereich Informatik > Graphisch-Interaktive Systeme
Hinterlegungsdatum: 16 Apr 2018 09:03
Letzte Änderung: 16 Apr 2018 09:03
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