In this thesis, we present a complete framework to inverse render faces with a 3D Morphable Model. By decomposing the image formation process into a geometric and photometric part, we are able to state the problem as a multilinear system which can be solved accurately and efficiently. As we treat each contribution as independent, the objective function is convex in the parameters and a globally optimal solution can be found. We start by recovering 3D shape using a novel algorithm which incorporates generalisation errors of the model obtained from empirical measurements. The algorithm is extended so it can efficiently deal with mixture distributions. We then describe three methods to recover facial texture, and for the second and third, diffuse lighting, specular reflectance and camera properties from a single image. These methods make increasingly weak assumptions and can all be solved in a linear fashion. We further modify our framework so it accounts for global illumination effects. This is achieved by incorporating statistical models for ambient occlusion and bent normals into the image formation model. We show that solving for ambient occlusion and bent normal parameters as part of the fitting process improves the accuracy of the estimated texture map and illumination environment. We present results on challenging data, rendered under complex natural illumination with both specular reflectance and occlusion of the illumination environment. We evaluate our findings on publicly available datasets, where we are able to obtain state-ofthe-art results. Finally, we present a practical method to synthesise a larger population from a small training-set and show how the new instances can be used to build a flexible PCA model.

In this paper, we present a robust and efficient method to statistically recover the full 3D shape and texture of faces from single 2D images. We separate shape and texture recovery into two linear problems. For shape recovery, we learn empirically the generalization error of a 3D morphable model using out-of-sample data. We use this to predict the 2D variance associated with a sparse set of 2D feature points. This knowledge is incorporated into a parameter-free probabilistic framework which allows 3D shape recovery of a face in an arbitrary pose in a single step. Under the assumption of diffuseonly reflectance, we also show how photometric invariants can be used to recover texture parameters in an illumination insensitive manner. We present empirical results with comparison to the state-of-the-art analysis-by-synthesis methods and show an application of our approach to adjusting the pose of subjects in oil paintings.

No abstract

Well known results in inverse rendering show that recovery of unconstrained illumination, texture and reflectance properties from a single image is ill-posed. On the other hand, in the domain of faces linear statistical models have been shown to efficiently characterise variations in face shape and texture. In this paper we show how the inverse rendering process can be constrained using a morphable model of face shape and texture. Starting with a shape estimate recovered using the statistical shape model, we show that the image formation process leads to a system of equations which is multilinear in the unknowns. We are able to estimate diffuse texture, specular reflectance properties, the illumination environment and camera properties from a single image. Our approach uses relaxed assumptions and offers improved performance in comparison to the current state-of-the-art morphable model fitting algorithms.

No abstract