3D morphable face models revisited

In this paper we revisit the process of constructing a high resolution 3D morphable model of face shape variation. We demonstrate how the statistical tools of thin-plate splines and Procrustes analysis can be used to construct a morphable model that is both more efficient and generalises to novel face surfaces more accurately than previous models. We also reformulate the probabilistic prior that the model provides on the distribution of parameter vector lengths. This distribution is determined solely by the number of model dimensions and can be used as a regularisation constraint in fitting the model to data without the need to empirically choose a parameter controlling the trade off between plausibility and quality of fit. As an example application of this improved model, we show how it may be fitted to a sparse set of 2D feature points (approximately 100). This provides a rapid means to estimate high resolution 3D face shape for a face in any pose given only a single face image. We present experimental results using ground truth data and hence provide absolute reconstruction errors. On average, the per vertex error of the reconstructed faces is less than 3.6 mm.

1. Introduction

The problem of estimating 3-dimensional face shape from one or more images has attracted considerable attention in recent years [4], [8], [10], [11], [18], [19]. The primary motivation for this work is that 3D shape information provides a pose and illumination invariant description of a face, which can either be used for recognition directly [4], [7], [18], or to produce illumination and pose normalised images for input to a 2D recognition system [2], [18], [19]. The benefits of such an approach are improved robustness to changes in pose, illumination and expression, while still only requiring a single intensity image as input.