The Bi-directional Framework for Unifying Parametric Image Alignment Approaches

In this paper, a generic bi-directional framework is proposed for parametric image alignment, that extends the classification of [1]. Four main categories (Forward, Inverse, Dependent and Bi-directional) form the basis of a consistent set of subclasses, onto which state-of-theart methods have been mapped. New formulations for the ESM [2] and the Inverse Additive [3] algorithms are proposed, that show the ability of this framework to unify existing approaches. New explicit equivalence relationships are given for the case of first-order optimization that provide some insights into the choice of an update rule in iterative algorithms.

• Type: Conference
• Year: 2008
• Where: ECCV
• Authors: Jean-Baptiste Authesserre, Rémi Mégret, Yannick Berthoumieu
• Keywords: Computer Vision, ECCV 2008, Explicit Equivalence Relationships, First-order Optimization, Generic Bi-directional Framework, Iterative Algorithms, Parametric Image Alignment