In this paper, we introduce a novel 2D-3D hybrid video stabilization method which combines virtues of 2D and 3D video stabilization methods in one routine. It attempts to achieve high-quality camera motions and to retain full frame coherence in each frame, at while, ensure that local regions undergo a similarity transformation. We solve the stabilization problem by integrating 3D and 2D video stabilization methods into one routine. It smooths camera motions and explicitly employs local motion information which constraints video frames to be temporal coherent, and achieves high-quality video stabilization. Experiments s how t hat our method not only can achieve high-quality camera motion on good 3D reconstructed scene, but also can deal with complicated videos containing near, large moving objects.
展开▼