Fast and exact Bi-directional Fitting of Active Appearance Models

Jean Kossaifi, Georgios Tzimiropoulos, Maja Pantic

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

    9 Citations (Scopus)
    71 Downloads (Pure)


    Finding landmarks on objects like faces is a challenging computer vision problem, especially in real life conditions (or in-the-wild) and Active Appearance Models have been widely used to solve it. State-of-the-art algorithms for fitting an AAM to a new image are based on Gauss-Newton (GN) optimization. Recently fast GN algorithms have been proposed for both forward additive and inverse compositional fitting frameworks. In this paper, we propose a fast and exact bi-directional (Fast-Bd) approach to AAM fitting by combining both approaches. Although such a method might appear to increase computational burden, we show that by capitalizing on results from optimization theory, an exact solution, as computationally efficient as the original forward or inverse formulation, can be derived. Our proposed bi-directional approach achieves state-of-the-art performance and superior convergence properties. These findings are validated on two challenging, in-the-wild data sets, LFPW and Helen, and comparison is provided to the state-of-the art methods for Active Appearance Models fitting.
    Original languageUndefined
    Title of host publicationProceedings of IEEE International Conference on Image Processing (ICIP 2015)
    Place of PublicationUSA
    Number of pages5
    ISBN (Print)978-1-4799-8339-1
    Publication statusPublished - Sept 2015
    EventIEEE International Conference on Image Processing, ICIP 2015 - Quebec City, Canada
    Duration: 27 Sept 201530 Sept 2015

    Publication series

    PublisherIEEE Computer Society


    ConferenceIEEE International Conference on Image Processing, ICIP 2015
    Abbreviated titleICIP
    CityQuebec City


    • inverse compositional
    • bi-directional fitting
    • EWI-26776
    • EC Grant Agreement nr.: FP7/611153
    • EC Grant Agreement nr.: FP7/2007-2013
    • METIS-316029
    • IR-99506
    • Active Appearance Models
    • GaussNewton
    • forward additive
    • HMI-HF: Human Factors

    Cite this