Motion Estimation with Non-Local Total Variation Regularization
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}
}
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.
January 20, 2011 by hgpu
