Autocorrespondence: feature-based match estimation and image metamorphosis

This paper addresses the problem of matching distinct but related objects across images, for applications such as view-based model capture, virtual presence, and morphing special effects. A new approach to match estimation is presented for estimating correspondences between distinct objects. This approach minimizes the effects of lighting variations and nonrigid deformations. A sparse set of features are used for alignment, followed by image-plane warping, or morphing, based on these constraints.