\input zb-basic
\input zb-ioport
\iteman{io-port 06069821}
\itemau{H\'eas, P.; Herzet, C.; M\'emin, E.}
\itemti{Robust optic-flow estimation with Bayesian inference of model and hyper-parameters.}
\itemso{Bruckstein, Alfred M. (ed.) et al., Scale space and variational methods in computer vision. Third international conference, SSVM 2011, Ein-Gedi, Israel, May 29--June 2, 2011. Revised selected papers. Berlin: Springer (ISBN 978-3-642-24784-2/pbk). Lecture Notes in Computer Science 6667, 773-785 (2012).}
\itemab
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.
\itemrv{~}
\itemcc{}
\itemut{motion modeling; marginalized posterior; Bayesian inference; regularization coefficients; robust hyper-parameters; cost-functions}
\itemli{doi:10.1007/978-3-642-24785-9\_65}
\end