TY - GEN
T1 - Fast and exact Bi-directional Fitting of Active Appearance Models
AU - Kossaifi, Jean
AU - Tzimiropoulos, Georgios
AU - Pantic, Maja
N1 - eemcs-eprint-26776
PY - 2015/9
Y1 - 2015/9
N2 - 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.
AB - 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.
KW - inverse compositional
KW - bi-directional fitting
KW - EWI-26776
KW - EC Grant Agreement nr.: FP7/611153
KW - EC Grant Agreement nr.: FP7/2007-2013
KW - METIS-316029
KW - IR-99506
KW - Active Appearance Models
KW - GaussNewton
KW - forward additive
KW - HMI-HF: Human Factors
U2 - 10.1109/ICIP.2015.7350977
DO - 10.1109/ICIP.2015.7350977
M3 - Conference contribution
SN - 978-1-4799-8339-1
SP - 1135
EP - 1139
BT - Proceedings of IEEE International Conference on Image Processing (ICIP 2015)
PB - IEEE
CY - USA
T2 - IEEE International Conference on Image Processing, ICIP 2015
Y2 - 27 September 2015 through 30 September 2015
ER -