2543

Motion Estimation with Non-Local Total Variation Regularization

Manuel Werlberger, Thomas Pock, Horst Bischof
Institute for Computer Graphics and Vision
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2010

@conference{werlberger2010motion,

   title={Motion estimation with non-local total variation regularization},

   author={Werlberger, M. and Pock, T. and Bischof, H.},

   booktitle={Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on},

   pages={2464–2471},

   issn={1063-6919},

   year={2010},

   organization={IEEE}

}

Download Download (PDF)   View View   Source Source   

680

views

State-of-the-art motion estimation algorithms suffer from three major problems: Poorly textured regions, occlusions and small scale image structures. Based on the Gestalt principles of grouping we propose to incorporate a low level image segmentation process in order to tackle these problems. Our new motion estimation algorithm is based on non-local total variation regularization which allows us to integrate the low level image segmentation process in a unified variational framework. Numerical results on the Middlebury optical flow benchmark data set demonstrate that we can cope with the aforementioned problems.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2017 hgpu.org

All rights belong to the respective authors

Contact us: