The bi-directional framework for unifying parametric image alignment approaches - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2008

The bi-directional framework for unifying parametric image alignment approaches

Résumé

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-the-art 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.

Dates et versions

hal-00331885 , version 1 (19-10-2008)

Identifiants

Citer

Rémi Mégret, Jean-Baptiste Authesserre, Yannick Berthoumieu. The bi-directional framework for unifying parametric image alignment approaches. 10th European Conference on Computer Vision (ECCV 2008), Oct 2008, Marseille, France. pp.400-411, ⟨10.1007/978-3-540-88690-7_30⟩. ⟨hal-00331885⟩
250 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More