Continuous Regression for Non-Rigid Image Alignment

October 2012

Continuous Regression for Non-Rigid Image Alignment

Authors:

E. Sanchez, F. De La Torre, and D. Gonzalez
Conference Paper
Proceedings of (ECCV) European Conference on Computer Vision

Abstract:

Parameterized Appearance Models (PAMs) such as Active Appearance Models (AAMs), Morphable Models and Boosted Appearance Models have been extensively used for face alignment. Broadly speaking, PAMs methods can be classified into generative and discriminative. Discriminative methods learn a mapping between appearance features and motion parameters (rigid and non-rigid). While discriminative approaches have some advantages (e.g., feature weighting, improved generalization), they suffer from two major drawbacks: (1) they need large amounts of perturbed samples to train a regressor or classifier, making the training process computationally expensive in space and time. (2) It is not practical to uniformly sample the space of motion parameters. In practice, there are regions of the motion space that are more densely sampled than others, resulting in biased models and lack of generalization. To solve these problems, this paper proposes a computationally efficient continuous regressor that does not require the sampling stage. Experiments on real data show the improvement in memory and time requirements to train a discriminative appearance model, as well as improved generalization.
@conference{Sanchez-2012-120907,
author = {E. Sanchez And F. De La Torre And D. Gonzalez},
title = {Continuous Regression for Non-Rigid Image Alignment},
booktitle = {Proceedings of (ECCV) European Conference on Computer Vision},
year = {2012},
month = {October},
pages = {250 - 263},
}
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.