Optimization problems for fast AAM fitting in-the-wild

Tzimiropoulos, Georgios; Pantic, Maja

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.

Citation

Tzimiropoulos, G., & Pantic, M. Optimization problems for fast AAM fitting in-the-wild. Presented at 2013 IEEE International Conference on Computer Vision (ICCV)

• Conference Name: 2013 IEEE International Conference on Computer Vision (ICCV)
• End Date: Dec 8, 2013
• Publication Date: Jan 1, 2013
• Deposit Date: Jan 29, 2016
• Publicly Available Date: Jan 29, 2016
• Peer Reviewed: Peer Reviewed
• Public URL: https://nottingham-repository.worktribe.com/output/1005671
• Publisher URL: http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6751183&filter=AND%28p_Publication_Number:6750807%29
• Additional Information: (c) 2013 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.