Abstract

We propose a novel motion model, SteadyFlow, to represent the motion between neighboring video frames for stabilization. A SteadyFlow is a specifific optical flflow by enforcing strong spatial coherence, such that smoothing feature trajectories can be replaced by smoothing pixel pro- fifiles, which are motion vectors collected at the same pixel location in the SteadyFlow over time. In this way, we can avoid brittle feature tracking in a video stabilization system. Besides, SteadyFlow is a more general 2D motion model which can deal with spatially-variant motion. We initialize the SteadyFlow by optical flflow and then discard discontinuous motions by a spatial-temporal analysis and fifill in missing regions by motion completion. Our experiments demonstrate the effectiveness of our stabilization on real-world challenging videos