Manifold-based constraints for operations in face space

PATTERN RECOGNITION

卷:52

Article

Patel, Ankur¹  Smith, William A. P.² 

[1] Conversant Inc, 101 North Wacker,23rd Floor, Chicago, IL 60606 USA

[2] Univ York, Dept Comp Sci, Deramore Lane, York YO105GH, N Yorkshire, England

关键词: Optimisation on manifolds;    Face space;    3D morphable models;    Constrained optimisation;    Statistical modelling;   

DOI  :  10.1016/j.patcog.2015.10.003

来源: Elsevier

【 摘 要 】

In this paper, we constrain faces to points on a manifold within the parameter space of a linear statistical model. The manifold is the subspace of faces which have maximally likely distinctiveness and different points correspond to unique identities. We provide a detailed empirical validation for the chosen manifold. We show how the Log and Exponential maps for a hyperspherical manifold can be used to replace linear operations such as warping and averaging with operations on this manifold. Finally, we use the manifold to develop a new method for fitting a statistical face shape model to data, which is both robust (avoids overfitting) and overcomes model dominance (is not susceptible to local minima close to the mean face). We provide experimental results for fitting a dense 3D morphable face model to data using two different objective functions (one underconstrained and one with many local minima). Our method outperforms generic nonlinear optimisers based on the BFGS Quasi-Newton method and the Levenberg-Marquardt algorithm when fitting using the Basel Face Model. (C) 2015 Elsevier Ltd. All rights reserved.

【 授权许可】

Free