About: Curvature Prior for MRF-based Segmentation and Shape Inpainting

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: Curvature Prior for MRF-based Segmentation and Shape Inpainting Goto Sponge NotDistinct Permalink

An Entity of Type : http://linked.opendata.cz/ontology/domain/vavai/Vysledek, within Data Space : linked.opendata.cz associated with source document(s)

Attributes	Values
rdf:type	skos:Concept http://linked.opendata.cz/ontology/domain/vavai/Vysledek
Description	Most image labeling problems such as segmentation and image reconstruction are fundamentally ill-posed and suffer from ambiguities and noise. Higher order image priors encode high level structural dependencies between pixels and are key to overcoming these problems. However, these priors in general lead to computationally intractable models. This paper addresses the problem of discovering compact representations of higher order priors which allow efficient inference. We propose a framework for solving this problem which uses a recently proposed representation of higher order functions where they are encoded as lower envelopes of linear functions. Maximum a Posterior inference on our learned models reduces to minimizing a pairwise function of discrete variables, which can be done approximately using standard methods. We show that our framework can learn a compact representation that approximates a prior that encourages low curvature shapes. We evaluate the approximation accuracy, discuss properties of the trained model, and demonstrate it on shape inpainting and image segmentation problems. Most image labeling problems such as segmentation and image reconstruction are fundamentally ill-posed and suffer from ambiguities and noise. Higher order image priors encode high level structural dependencies between pixels and are key to overcoming these problems. However, these priors in general lead to computationally intractable models. This paper addresses the problem of discovering compact representations of higher order priors which allow efficient inference. We propose a framework for solving this problem which uses a recently proposed representation of higher order functions where they are encoded as lower envelopes of linear functions. Maximum a Posterior inference on our learned models reduces to minimizing a pairwise function of discrete variables, which can be done approximately using standard methods. We show that our framework can learn a compact representation that approximates a prior that encourages low curvature shapes. We evaluate the approximation accuracy, discuss properties of the trained model, and demonstrate it on shape inpainting and image segmentation problems. (en)
Title	Curvature Prior for MRF-based Segmentation and Shape Inpainting Curvature Prior for MRF-based Segmentation and Shape Inpainting (en)
skos:prefLabel	Curvature Prior for MRF-based Segmentation and Shape Inpainting Curvature Prior for MRF-based Segmentation and Shape Inpainting (en)
skos:notation	RIV/68407700:21230/12:00200404!RIV13-MSM-21230___
http://linked.open...avai/predkladatel	Fakulta elektrotechnická
http://linked.open...avai/riv/aktivita	P
http://linked.open...avai/riv/aktivity	P(7E10044)
http://linked.open...vai/riv/dodaniDat	2013
http://linked.open...aciTvurceVysledku	Shekhovtsov, Oleksandr
http://linked.open.../riv/druhVysledku	D - Článek ve sborníku
http://linked.open...iv/duvernostUdaju	S - Úplné a pravdivé údaje nepodléhající ochraně podle zvláštních právních předpisů
http://linked.open...titaPredkladatele	České vysoké učení technické v Praze / Fakulta elektrotechnická
http://linked.open...dnocenehoVysledku	129300
http://linked.open...ai/riv/idVysledku	RIV/68407700:21230/12:00200404
http://linked.open...riv/jazykVysledku	eng - angličtina
http://linked.open.../riv/klicovaSlova	image labeling; segmentation; shape Inpainting; MFR (en)
http://linked.open.../riv/klicoveSlovo	segmentation MFR image labeling shape Inpainting
http://linked.open...ontrolniKodProRIV	[217E5D33D003]
http://linked.open...v/mistoKonaniAkce	Graz
http://linked.open...i/riv/mistoVydani	Heidelberg
http://linked.open...i/riv/nazevZdroje	DAGM/OAGM 2012: Pattern Recognition - Joint 34th DAGM and 36th OAGM Symposium
http://linked.open...in/vavai/riv/obor	JD
http://linked.open...ichTvurcuVysledku	1 (xsd:int)
http://linked.open...cetTvurcuVysledku	3 (xsd:int)
http://linked.open...vavai/riv/projekt	Natural human-robot cooperation in dynamic environments
http://linked.open...UplatneniVysledku	2012
http://linked.open...iv/tvurceVysledku	Shekhovtsov, Oleksandr Kohli, P. Rother, C.
http://linked.open...vavai/riv/typAkce	WRD - Světová
http://linked.open.../riv/zahajeniAkce	2012-08-29 (xsd:date)
issn	0302-9743
number of pages	11 (xsd:int)
http://purl.org/ne...btex#hasPublisher	Springer-Verlag
https://schema.org/isbn	978-3-642-32716-2
http://localhost/t...ganizacniJednotka	21230
is http://linked.open...avai/riv/vysledek of	Curvature Prior for MRF-based Segmentation and Shape Inpainting

Faceted Search & Find service v1.16.118 as of Jun 21 2024

Alternative Linked Data Documents: ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 07.20.3240 as of Jun 21 2024, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (126 GB total memory, 112 GB memory in use)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software