%0 Conference Proceedings
%F Heas11a
%A Héas, P.
%A Herzet, C.
%A Mémin, E.
%T Robust optic-flow estimation with Bayesian inference of model and hyper-parameters
%B Proc. Conf. Scale-Space and Variational Meth. (SSVM'11)
%C Israel
%X 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 “Middle- bury” 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.
%U http://www.irisa.fr/fluminance/publi/papers/2011_SSVM_heas.pdf
%8 June
%D 2011