Fast and exact bi-directional fitting of active appearance models

Kossaifi, Jean; Tzimiropoulos, Georgios; Pantic, Maja

Abstract

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.

Citation

Kossaifi, J., Tzimiropoulos, G., & Pantic, M. (2015). Fast and exact bi-directional fitting of active appearance models.

• Conference Name: IEEE International Conference on Image Processing (ICIP 2015)
• End Date: Sep 30, 2015
• Publication Date: Sep 28, 2015
• Deposit Date: Jan 29, 2016
• Publicly Available Date: Jan 29, 2016
• Peer Reviewed: Peer Reviewed
• Keywords: active appearance models, Gauss-Newton, forward additive, inverse compositional, bi-directional fitting
• Public URL: https://nottingham-repository.worktribe.com/output/760530
• Additional Information: © 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, 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 component of this work in other works.