A Variational Approach to Blending Based on Warping for Non-Overlapped Images

By Chang-Ock Lee, Kiwan Jeon, Youngsoo Ha and Jooyoung Hahn
Division of Applied Mathematics, KAIST, Daejeon, 305-701, Korea

Computer Vision and Image Understanding, V. 105 (2007) pp. 112-120



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 the work by Liao et al. 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.

Click images to see the movies of the examples in the paper.