Sciweavers

Share
DAGM
2008
Springer

An Unbiased Second-Order Prior for High-Accuracy Motion Estimation

11 years 8 months ago
An Unbiased Second-Order Prior for High-Accuracy Motion Estimation
Abstract. Virtually all variational methods for motion estimation regularize the gradient of the flow field, which introduces a bias towards piecewise constant motions in weakly textured areas. We propose a novel regularization approach, based on decorrelated second-order derivatives, that does not suffer from this shortcoming. We then derive an efficient numerical scheme to solve the new model using projected gradient descent. A comparison to a TV regularized model shows that the proposed second-order prior exhibits superior performance, in particular in lowtextured areas (where the prior becomes important). Finally, we show that the proposed model yields state-of-the-art results on the Middlebury optical flow database.
Werner Trobin, Thomas Pock, Daniel Cremers, Horst
Added 19 Oct 2010
Updated 19 Oct 2010
Type Conference
Year 2008
Where DAGM
Authors Werner Trobin, Thomas Pock, Daniel Cremers, Horst Bischof
Comments (0)
books