Motion Estimation with Non-Local Total Variation Regularization

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 uni?ed variational framework. Numerical results on the Middlebury optical flow benchmark data set demonstrate that we can cope with the aforementioned problems.

• Type: Conference
• Year: 2010
• Where: CVPR
• Authors: Manuel Werlberger, Thomas Pock, Horst Bischof
• Keywords: Computer Vision, CVPR 2010, GPU, Nonlocal, Optical Flow, Total Variation