Rationalizing Efficient Compositional Image Alignment

Enrique Muñoz

doi:10.1007/s11263-014-0769-6

Return

Rationalizing Efficient Compositional Image Alignment

2014-10-04

PRE

Enrique Muñoz

Pablo Márquez-Neila

Luis Baumela *

DOI：10.1007/s11263-014-0769-6

Original

Original request for help

Save

Abstract

En 中文

We study the issue of computational efficiency for Gauss-Newton (GN) non-linear least-squares optimization in the context of image alignment. We introduce the Constant Jacobian Gauss-Newton (CJGN) optimization, a GN scheme with constant Jacobian and Hessian matrices, and the equivalence and independence conditions as the necessary requirements that any function of residuals must satisfy to be optimized with this efficient approach. We prove that the Inverse Compositional (IC) image alignment algorithm is an instance of a CJGN scheme and formally derive the compositional and extended brightness constancy assumptions as the necessary requirements that must be satisfied by any image alignment problem so it can be solved with an efficient compositional scheme. Moreover, in contradiction with previous results, we also prove that the forward and inverse compositional algorithms are not equivalent. They are equivalent, however, when the extended brightness constancy assumption is satisfied. To analyze the impact of the satisfaction of these requirements we introduce a new image alignment evaluation framework and the concepts of short- and wide-baseline Jacobian. In wide-baseline Jacobian problems the optimization will diverge if the requirements are not satisfied. However, with a good initialization, a short-baseline Jacobian problem may converge even if the requirements are not satisfied.

Keywords:

Image registration

Tracking

Efficient Gauss-Newton optimization

Efficient compositional image alignment

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.