@InProceedings{shekhovtsov-2012-curvature,
  IS = { zkontrolovano 14 Jan 2013 },
  UPDATE  = { 2012-10-01 },
  author =      {Shekhovtsov, Alexander and Kohli, Pushmeet and Rother, Carsten },
  title =       {Curvature Prior for {MRF}-based Segmentation and Shape Inpainting},
  year =        {2012},
  pages =       {41-51},
  doi =         {10.1007/978-3-642-32717-9},
  booktitle =   {DAGM/OAGM 2012: Pattern Recognition - Joint 34th DAGM and 36th OAGM Symposium},
  editor =      {Pinz, Axel and Pock, Thomas and Bischof, Horst and Leberl, Franz},
  publisher =   {Springer},
  address =     {Heidelberg, Germany},
  isbn =        {978-3-642-32716-2},
  issn =        {0302-9743},
  volume =      {7476},
  series =      {Lecture Notes in Computer Science},
  book_pages =  {525},
  day =         {29-31},
  month =       {August},
  annote =      {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.},
  project =     {FP7-ICT-247870 NIFTi},
  acceptance_ratio = {0.45},
}