Feature displacement interpolation

Abstract
Given a sparse set of feature matches, we want tocompute an interpolated dense displacement map. Theapplication may be stereo disparity computation, flowcomputation, or non-rigid medical registration. Alsoestimation of missing image data, may be phrasedin this framework. Since the features often are verysparse, the interpolation model becomes crucial. Weshow that a maximum likelihood estimation based onthe covariance properties (Kriging) show propertiesmore expedient than methods such...

This publication has 7 references indexed in Scilit: