AOMs Generic Face Alignment (2012)

This code reproduces the experiments reported in the paper "Generic Active Appearance Models Revisited", presented at ACCV 2012. The MATLAB implementation was written by Joan Alabort-i-Medina and Georgios Tzimiropoulos.  MATLAB version 7.11.0 (R2012a) or later is needed in order to run the code.

 

Description:

 

Active Orientation Models (AOMs) are generative models of facial shape and appearance. Their main differences with the well-known paradigm of Active Appearance Models (AAMs)  are :

  1. They use a different statistical model of appearance.
  2.  They areaccompanied by a robust algorithm for model  fitting and parameter estimation
  3.  Most importantly, they generalize well to unseenfaces and variations.

 

Their main similarity is computational complexity. The project-out version of AOMs is as computationally efficient asthe standard project-out inverse compositional algorithm which is admittedly the fastest algorithm for fitting AAMs.

Download