Combined spline- and block-based motion estimation for video coding

We propose a technique to estimate motion for video coding. Our technique combines spline-based registration and block matching motion estimation. It replaces the initial compute-intensive gross block matching search with spline-based registration, which is more efficient in recovering full-image motion fields. This results in a smooth motion field representative of the true motion in the scene, which can be more efficiently encoded and be guaranteed of high visual quality as well. Furthermore, the implementation is computationally cost-effective. Experimental results on well-known test image sequences show that the method results in an increase in coding efficiency along with a reduction in computational cost.