Supervised Descent Method and its Applications to Face Alignment - Robotics Institute Carnegie Mellon University

Supervised Descent Method and its Applications to Face Alignment

Conference Paper, Proceedings of (CVPR) Computer Vision and Pattern Recognition, pp. 532 - 539, June, 2013

Abstract

Many computer vision problems (e.g., camera calibration, image alignment, structure from motion) are solved through a nonlinear optimization method. It is generally accepted that 2nd order descent methods are the most robust, fast and reliable approaches for nonlinear optimization of a general smooth function. However, in the context of computer vision, 2nd order descent methods have two main drawbacks: (1) The function might not be analytically differentiable and numerical approximations are impractical. (2) The Hessian might be large and not positive definite. To address these issues, this paper proposes a Supervised Descent Method (SDM) for minimizing a Non-linear Least Squares (NLS) function. During training, the SDM learns a sequence of descent directions that minimizes the mean of NLS functions sampled at different points. In testing, SDM minimizes the NLS objective using the learned descent directions without computing the Jacobian nor the Hessian. We illustrate the benefits of our approach in synthetic and real examples, and show how SDM achieves state-of-the-art performance in the problem of facial feature detection. The code is available at www.humansensing.cs. cmu.edu/intraface.

BibTeX

@conference{Xiong-2013-7701,
author = {Xuehan Xiong and Fernando De la Torre Frade},
title = {Supervised Descent Method and its Applications to Face Alignment},
booktitle = {Proceedings of (CVPR) Computer Vision and Pattern Recognition},
year = {2013},
month = {June},
pages = {532 - 539},
keywords = {tracking, face alignment, facial feature detection, nonlinear least squares},
}