A variational approach to blending based on warping for non-overlapped images

This paper presents a new model for image blending based on warping. The model is represented by partial differential equations (PDEs) and gives a sequence of images, which has the properties of both blending of image intensities and warping of image shapes. We modified the energy functional in [1] in order to adapt the idea of the shape warping to the image blending. The PDEs from the proposed energy functional cover not only overlapped images but also non-overlapped ones. 1 Variational Formulations Given two shapes S and T in the domain Ω, so called the source and the target, respectively, we define φ(x) and ψ(x), x ∈ R, to be signed distance functions having zero values on each shape boundary. To match two shapes, we find two deformation fields u(x) and v(x) ∈ R for the source and the target, respectively, by minimizing the energy functional