High Accuracy Optical Flow Estimation Based on a Theory for Warping

Abstract. We study an energy functional for computing optical flow that combines three assumptions: a brightness constancy assumption, a gradient constancy assumption, and a discontinuity-preserving spatio-temporal smoothness constraint. In order to allow for large displacements, linearisations in the two data terms are strictly avoided. We present a consistent numerical scheme based on two nested fixed point iterations. By proving that this scheme implements a coarse-to-fine warping strategy, we give a theoretical foundation for warping which has been used on a mainly experimental basis so far. Our evaluation demonstrates that the novel method gives significantly smaller angular errors than previous techniques for optical flow estimation. We show that it is fairly insensitive to parameter variations, and we demonstrate its excellent robustness under noise. In Proc. 8th European Conference on Computer Vision, Springer LNCS 3024, T. Pajdla and J. Matas (Eds.), vol. 4, pp. 25-36, Prague,...

• Type: Conference
• Year: 2004
• Where: ECCV
• Authors: Thomas Brox, Andrés Bruhn, Nils Papenberg, Joachim Weickert
• Keywords: Brightness Constancy Assumption, Computer Vision, Consistent Numerical Scheme, ECCV 2004, Gradient Constancy Assumption, Optical Flow Estimation, Spatio-temporal Smoothness Constraint