A unified framework for compositional fitting of active appearance models
File(s)
Published version
Author(s)
Alabort-i-Medina, J
Zafeiriou, S
Type
Journal Article
Abstract
Active Appearance Models (AAMs) are
one of the most popular and well-established techniques
for modeling deformable objects in computer vision. In
this paper, we study the problem of fitting AAMs using
Compositional Gradient Descent (CGD) algorithms. We
present a unified and complete view of these algorithms
and classify them with respect to three main characteristics:
i) cost function; ii) type of composition; and
iii) optimization method. Furthermore, we extend the
previous view by: a) proposing a novel Bayesian cost
function that can be interpreted as a general probabilistic
formulation of the well-known project-out loss;
b) introducing two new types of composition, asymmetric
and bidirectional, that combine the gradients of both
image and appearance model to derive better convergent
and more robust CGD algorithms; and c) providing
new valuable insights into existent CGD algorithms
by reinterpreting them as direct applications of
the Schur complement and the Wiberg method. Finally,
in order to encourage open research and facilitate future
comparisons with our work, we make the implementation
of the algorithms studied in this paper publicly
available as part of the Menpo Project1
.
one of the most popular and well-established techniques
for modeling deformable objects in computer vision. In
this paper, we study the problem of fitting AAMs using
Compositional Gradient Descent (CGD) algorithms. We
present a unified and complete view of these algorithms
and classify them with respect to three main characteristics:
i) cost function; ii) type of composition; and
iii) optimization method. Furthermore, we extend the
previous view by: a) proposing a novel Bayesian cost
function that can be interpreted as a general probabilistic
formulation of the well-known project-out loss;
b) introducing two new types of composition, asymmetric
and bidirectional, that combine the gradients of both
image and appearance model to derive better convergent
and more robust CGD algorithms; and c) providing
new valuable insights into existent CGD algorithms
by reinterpreting them as direct applications of
the Schur complement and the Wiberg method. Finally,
in order to encourage open research and facilitate future
comparisons with our work, we make the implementation
of the algorithms studied in this paper publicly
available as part of the Menpo Project1
.
Date Issued
2016-06-09
Date Acceptance
2016-05-18
Citation
International Journal of Computer Vision, 2016, 121 (1), pp.26-64
ISSN
1573-1405
Publisher
Springer Verlag (Germany)
Start Page
26
End Page
64
Journal / Book Title
International Journal of Computer Vision
Volume
121
Issue
1
Copyright Statement
© The Author(s) 2016. This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.
Sponsor
Engineering & Physical Science Research Council (EPSRC)
Engineering & Physical Science Research Council (EPSRC)
Commission of the European Communities
Grant Number
EP/J017787/1
EP/L026813/1
688520
Subjects
Science & Technology
Technology
Computer Science, Artificial Intelligence
Computer Science
Active appearance models
Non-linear optimization
Compositional gradient descent
Bayesian inference
Asymmetric and bidirectional composition
Schur complement
Wiberg algorithm
COMPONENT ANALYSIS
0801 Artificial Intelligence And Image Processing
Artificial Intelligence & Image Processing
Publication Status
Published