Abstract
In this paper we introduce a novel higher-order regulariza- tion term. The proposed regularizer is a non-local extension of the pop- ular second-order Total Generalized variation, which favors piecewise affine solutions and allows to incorporate soft-segmentation cues into the regularization term. These properties make this regularizer especially ap- pealing for optical flow estimation, where it offers accurately localized motion boundaries and allows to resolve ambiguities in the matching term. We additionally propose a novel matching term which is robust to illumination and scale changes, two ma jor sources of errors in optical flow estimation algorithms. We extensively evaluate the proposed regu- larizer and data term on two challenging benchmarks, where we are able to obtain state of the art results. Our method is currently ranked first among classical two-frame optical flow methods on the KITTI optical flow benchmark.