A global perspective on MAP inference for low level vision Conference Paper

Author(s): Woodford, Oliver J; Rother, Carsten; Kolmogorov, Vladimir
Title: A global perspective on MAP inference for low level vision
Abstract: In recent years the Markov Random Field (MRF) has become the de facto probabilistic model for low-level vision applications. However, in a maximum a posteriori (MAP) framework, MRFs inherently encourage delta function marginal statistics. By contrast, many low-level vision problems have heavy tailed marginal statistics, making the MRF model unsuitable. In this paper we introduce a more general Marginal Probability Field (MPF), of which the MRF is a special, linear case, and show that convex energy MPFs can be used to encourage arbitrary marginal statistics. We introduce a flexible, extensible framework for effectively optimizing the resulting NP-hard MAP problem, based around dual-decomposition and a modified mincost flow algorithm, and which achieves global optimality in some instances. We use a range of applications, including image denoising and texture synthesis, to demonstrate the benefits of this class of MPF over MRFs.
Keywords: NP-hard; Maximum a posteriori; Markov random field; Extensible framework; Flow algorithm; Global optimality; Global perspective; Heavy-tailed; Image de-noising; Low-level vision; Marginal probability; Probabilistic models; Texture synthesis
Conference Title: ICCV: International Conference on Computer Vision
Conference Dates: September 29 - October 2, 2009
Conference Location: Kyoto, Japan
Publisher: IEEE  
Date Published: 2009-05-01
Start Page: 2319
End Page: 2326
DOI: 10.1109/ICCV.2009.5459434
Open access: no
IST Austria Authors
Related IST Austria Work