Pose Invariant Deformable Shape Priors Using L1 Higher Order Sparse Graphs - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2013

Pose Invariant Deformable Shape Priors Using L1 Higher Order Sparse Graphs

Abstract

In this paper we propose a novel method for knowledge-based segmentation. We adopt a point distribution graphical model formulation which encodes pose invariant shape priors through L1 sparse higher order cliques. Local shape deformation properties of the model can be captured and learned in an optimal manner from a training set using dual decomposition. These higher order shape terms are combined with conventional visual ones aiming at maximizing the posterior segmentation likelihood. The considered graphical model is optimized using dual decomposition and is used towards 2D (computer vision) and 3D object segmentation (medical imaging) with promising results.
Fichier principal
Vignette du fichier
isvc382.pdf (1.53 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00856978 , version 1 (02-09-2013)

Identifiers

  • HAL Id : hal-00856978 , version 1

Cite

Bo Xiang, Nikos Komodakis, Nikos Paragios. Pose Invariant Deformable Shape Priors Using L1 Higher Order Sparse Graphs. 9th International Symposium on Visual Computing - ISVC 2013, Jul 2013, Rethymnon, Greece. ⟨hal-00856978⟩
263 View
261 Download

Share

Gmail Facebook X LinkedIn More