Optimization problems for fast AAM fitting in-the-wild

Georgios Tzimiropoulos, Maja Pantic

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

142 Citations (Scopus)
29 Downloads (Pure)

Abstract

We describe a very simple framework for deriving the most-well known optimization problems in Active Appearance Models (AAMs), and most importantly for providing efficient solutions. Our formulation results in two optimization problems for fast and exact AAM fitting, and one new algorithm which has the important advantage of being applicable to 3D. We show that the dominant cost for both forward and inverse algorithms is a few times mN which is the cost of projecting an image onto the appearance subspace. This makes both algorithms not only computationally realizable but also very attractive speed-wise for most current systems. Because exact AAM fitting is no longer computationally prohibitive, we trained AAMs in-the-wild with the goal of investigating whether AAMs benefit from such a training process. Our results show that although we did not use sophisticated shape priors, robust features or robust norms for improving performance, AAMs perform notably well and in some cases comparably with current state-of-the-art methods. We provide Matlab source code for training, fitting and reproducing the results presented in this paper at http://ibug.doc.ic.ac.uk/resources.
Original languageUndefined
Title of host publicationProceedings of the IEEE International Conference on Computer Vision, ICCV 2013
Place of PublicationUSA
PublisherIEEE Communications Society
Pages593-600
Number of pages8
ISBN (Print)1550-5499
DOIs
Publication statusPublished - 3 Dec 2013
EventIEEE International Conference on Computer Vision 2013 - Sydney Conference Centre, Sydney, Australia
Duration: 1 Dec 20138 Dec 2013
http://www.pamitc.org/iccv13/

Publication series

NameIEEE International Conference on Computer Vision
PublisherIEEE Communications Society
ISSN (Print)1550-5499

Conference

ConferenceIEEE International Conference on Computer Vision 2013
Abbreviated titleICCV 2013
CountryAustralia
CitySydney
Period1/12/138/12/13
Internet address

Keywords

  • HMI-HF: Human Factors
  • EWI-24238
  • METIS-302863
  • EC Grant Agreement nr.: FP7/2007-2013
  • IR-89696
  • EC Grant Agreement nr.: FP7/288235

Cite this

Tzimiropoulos, G., & Pantic, M. (2013). Optimization problems for fast AAM fitting in-the-wild. In Proceedings of the IEEE International Conference on Computer Vision, ICCV 2013 (pp. 593-600). (IEEE International Conference on Computer Vision). USA: IEEE Communications Society. https://doi.org/10.1109/ICCV.2013.79
Tzimiropoulos, Georgios ; Pantic, Maja. / Optimization problems for fast AAM fitting in-the-wild. Proceedings of the IEEE International Conference on Computer Vision, ICCV 2013. USA : IEEE Communications Society, 2013. pp. 593-600 (IEEE International Conference on Computer Vision).
@inproceedings{318cbb02c7b5488b8b310a6c7aada5f5,
title = "Optimization problems for fast AAM fitting in-the-wild",
abstract = "We describe a very simple framework for deriving the most-well known optimization problems in Active Appearance Models (AAMs), and most importantly for providing efficient solutions. Our formulation results in two optimization problems for fast and exact AAM fitting, and one new algorithm which has the important advantage of being applicable to 3D. We show that the dominant cost for both forward and inverse algorithms is a few times mN which is the cost of projecting an image onto the appearance subspace. This makes both algorithms not only computationally realizable but also very attractive speed-wise for most current systems. Because exact AAM fitting is no longer computationally prohibitive, we trained AAMs in-the-wild with the goal of investigating whether AAMs benefit from such a training process. Our results show that although we did not use sophisticated shape priors, robust features or robust norms for improving performance, AAMs perform notably well and in some cases comparably with current state-of-the-art methods. We provide Matlab source code for training, fitting and reproducing the results presented in this paper at http://ibug.doc.ic.ac.uk/resources.",
keywords = "HMI-HF: Human Factors, EWI-24238, METIS-302863, EC Grant Agreement nr.: FP7/2007-2013, IR-89696, EC Grant Agreement nr.: FP7/288235",
author = "Georgios Tzimiropoulos and Maja Pantic",
note = "eemcs-eprint-24238",
year = "2013",
month = "12",
day = "3",
doi = "10.1109/ICCV.2013.79",
language = "Undefined",
isbn = "1550-5499",
series = "IEEE International Conference on Computer Vision",
publisher = "IEEE Communications Society",
pages = "593--600",
booktitle = "Proceedings of the IEEE International Conference on Computer Vision, ICCV 2013",
address = "United States",

}

Tzimiropoulos, G & Pantic, M 2013, Optimization problems for fast AAM fitting in-the-wild. in Proceedings of the IEEE International Conference on Computer Vision, ICCV 2013. IEEE International Conference on Computer Vision, IEEE Communications Society, USA, pp. 593-600, IEEE International Conference on Computer Vision 2013, Sydney, Australia, 1/12/13. https://doi.org/10.1109/ICCV.2013.79

Optimization problems for fast AAM fitting in-the-wild. / Tzimiropoulos, Georgios; Pantic, Maja.

Proceedings of the IEEE International Conference on Computer Vision, ICCV 2013. USA : IEEE Communications Society, 2013. p. 593-600 (IEEE International Conference on Computer Vision).

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Optimization problems for fast AAM fitting in-the-wild

AU - Tzimiropoulos, Georgios

AU - Pantic, Maja

N1 - eemcs-eprint-24238

PY - 2013/12/3

Y1 - 2013/12/3

N2 - We describe a very simple framework for deriving the most-well known optimization problems in Active Appearance Models (AAMs), and most importantly for providing efficient solutions. Our formulation results in two optimization problems for fast and exact AAM fitting, and one new algorithm which has the important advantage of being applicable to 3D. We show that the dominant cost for both forward and inverse algorithms is a few times mN which is the cost of projecting an image onto the appearance subspace. This makes both algorithms not only computationally realizable but also very attractive speed-wise for most current systems. Because exact AAM fitting is no longer computationally prohibitive, we trained AAMs in-the-wild with the goal of investigating whether AAMs benefit from such a training process. Our results show that although we did not use sophisticated shape priors, robust features or robust norms for improving performance, AAMs perform notably well and in some cases comparably with current state-of-the-art methods. We provide Matlab source code for training, fitting and reproducing the results presented in this paper at http://ibug.doc.ic.ac.uk/resources.

AB - We describe a very simple framework for deriving the most-well known optimization problems in Active Appearance Models (AAMs), and most importantly for providing efficient solutions. Our formulation results in two optimization problems for fast and exact AAM fitting, and one new algorithm which has the important advantage of being applicable to 3D. We show that the dominant cost for both forward and inverse algorithms is a few times mN which is the cost of projecting an image onto the appearance subspace. This makes both algorithms not only computationally realizable but also very attractive speed-wise for most current systems. Because exact AAM fitting is no longer computationally prohibitive, we trained AAMs in-the-wild with the goal of investigating whether AAMs benefit from such a training process. Our results show that although we did not use sophisticated shape priors, robust features or robust norms for improving performance, AAMs perform notably well and in some cases comparably with current state-of-the-art methods. We provide Matlab source code for training, fitting and reproducing the results presented in this paper at http://ibug.doc.ic.ac.uk/resources.

KW - HMI-HF: Human Factors

KW - EWI-24238

KW - METIS-302863

KW - EC Grant Agreement nr.: FP7/2007-2013

KW - IR-89696

KW - EC Grant Agreement nr.: FP7/288235

U2 - 10.1109/ICCV.2013.79

DO - 10.1109/ICCV.2013.79

M3 - Conference contribution

SN - 1550-5499

T3 - IEEE International Conference on Computer Vision

SP - 593

EP - 600

BT - Proceedings of the IEEE International Conference on Computer Vision, ICCV 2013

PB - IEEE Communications Society

CY - USA

ER -

Tzimiropoulos G, Pantic M. Optimization problems for fast AAM fitting in-the-wild. In Proceedings of the IEEE International Conference on Computer Vision, ICCV 2013. USA: IEEE Communications Society. 2013. p. 593-600. (IEEE International Conference on Computer Vision). https://doi.org/10.1109/ICCV.2013.79