MRF-Based blind image deconvolution

Nikos Komodakis (1) , Nikos Paragios (2, 3)

1 ENPC - École des Ponts ParisTech
2 GALEN - Organ Modeling through Extraction, Representation and Understanding of Medical Image Content
3 CVN - Centre de vision numérique

This paper proposes an optimization-based blind image deconvolution method. The proposed method relies on imposing a discrete MRF prior on the deconvolved image. The use of such a prior leads to a very efficient and powerful deconvolution algorithm that carefully combines advanced optimization techniques. We demonstrate the extreme effectiveness of our method1 by applying it on a wide variety of very challenging cases that involve the inference of large and complicated blur kernels.

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Nikos Komodakis, Nikos Paragios. MRF-Based blind image deconvolution. 11th Asian Conference on Computer Vision - ACCV 2012, Nov 2012, Daejeon, North Korea. pp.361-374. ⟨hal-00856285⟩