Spanning the gap between motion estimation and morphing

Motion estimation is an important and well-studied method for determining correspondences between images in video processing. In contrast with motion estimation, the use of image warping on image sequences is a new and developing field. To provide image warping effects, morphing algorithms rely on mesh points to align two images. Presently, the selection of these mesh points is a labor-intensive, manual process. This paper attempts to automate the selection of mesh points for morphing by recognizing this problem as one of determining image correspondences. Applications include video compression, animation sequence generation and high-quality time dilation of video