@inbook {IOPORT.06069821,
    author       = {H\'eas, P. and Herzet, C. and M\'emin, E.},
    title        = {Robust optic-flow estimation with Bayesian inference of model and hyper-parameters.},
    year         = {2012},
    booktitle    = {Scale space and variational methods in computer vision. Third international conference, SSVM 2011, Ein-Gedi, Israel, May 29--June 2, 2011. Revised selected papers},
    isbn         = {978-3-642-24784-2},
    pages        = {773-785},
    publisher    = {Berlin: Springer},
    doi          = {10.1007/978-3-642-24785-9_65},
    abstract     = {Summary: Selecting optimal models and hyper-parameters is crucial for accurate optic-flow estimation. This paper solves the problem in a generic variational Bayesian framework. The method is based on a conditional model linking the image intensity function, the velocity field and the hyper-parameters characterizing the motion model. Inference is performed at three levels by considering maximum a posteriori problem of marginalized probabilities. We assessed the performance of the proposed method on image sequences of fluid flows and of the ``Middlebury'' database. Experiments prove that applying the proposed inference strategy on very simple models yields better results than manually tuning smoothing parameters or discontinuity preserving cost functions of classical state-of-the-art methods.},
    identifier   = {06069821},
}