In this paper, we present a novel open-source pipeline for face registration based on Gaussian processes as well as an application to face image analysis. Non-rigid registration of faces is significant for many applications in computer vision, such as the construction of 3D Morphable face models (3DMMs). Gaussian Process Morphable Models (GPMMs) unify a variety of non-rigid deformation models with B-splines and PCA models as examples. GPMM separate problem specific requirements from the registration algorithm by incorporating domain-specific adaptions as a prior model. The novelties of this paper are the following: (i) We present a strategy and modeling technique for face registration that considers symmetry, multiscale and spatially-varying details. The registration is applied to neutral faces and facial expressions. (ii) We release an open-source software framework for registration and modelbuilding, demonstrated on the publicly available BU3D-FE database. The released pipeline also contains an implementation of an Analysis-by-Synthesis model adaption of 2D face images, tested on the Multi-PIE and LFW database. This enables the community to reproduce, evaluate and compare the individual steps of registration to model-building and 3D/2D model fitting. (iii) Along with the framework release, we publish a new version of the Basel Face Model (BFM-2017) with an improved age distribution and an additional facial expression model.

In this article, we provide a detailed survey of 3D Morphable Face Models over the 20 years since they were first proposed. The challenges in building and applying these models, namely, capture, modeling, image formation, and image analysis, are still active research topics, and we review the state-of-the-art in each of these areas. We also look ahead, identifying unsolved challenges, proposing directions for future research, and highlighting the broad range of current and future applications.

We present a novel fully probabilistic method to interpret a single face image with the 3D Morphable Model. The new method is based on Bayesian inference and makes use of unreliable image-based information. Rather than searching a single optimal solution, we infer the posterior distribution of the model parameters given the target image. The method is a stochastic sampling algorithm with a propose-and-verify architecture based on the MetropolisHastings algorithm. The stochastic method can robustly integrate unreliable information and therefore does not rely on feed-forward initialization. The integrative concept is based on two ideas, a separation of proposal moves and their verification with the model (Data-Driven Markov Chain Monte Carlo), and filtering with the Metropolis acceptance rule. It does not need gradients and is less prone to local optima than standard fitters. We also introduce a new collective likelihood which models the average difference between the model and the target image rather than individual pixel differences. The average value shows a natural tendency towards a normal distribution, even when the individual pixel-wise difference is not Gaussian. We employ the new fitting method to calculate posterior models of 3D face reconstructions from single real-world images. A direct application of the algorithm with the 3D Morphable Model leads us to a fully automatic face recognition system with competitive performance on the Multi-PIE database without any database adaptation.

It is well known that deep learning approaches to face recognition suffer from various biases in the available training data. In this work, we demonstrate the large potential of synthetic data for analyzing and reducing the negative effects of dataset bias on deep face recognition systems. In particular we explore two complementary application areas for synthetic face images: 1) Using fully annotated synthetic face images we can study the face recognition rate as a function of interpretable parameters such as face pose. This enables us to systematically analyze the effect of different types of dataset biases on the generalization ability of neural network architectures. Our analysis reveals that deeper neural network architectures can generalize better to unseen face poses. Furthermore, our study shows that current neural network architectures cannot disentangle face pose and facial identity, which limits their generalization ability. 2) We pre-train neural networks with large-scale synthetic data that is highly variable in face pose and the number of facial identities. After a subsequent fine-tuning with realworld data, we observe that the damage of dataset bias in the real-world data is largely reduced. Furthermore, we demonstrate that the size of real-world datasets can be reduced by 75% while maintaining competitive face recognition performance. The data and software used in this work are publicly available 1 .

Faces in natural images are often occluded by a variety of objects. We propose a fully automated, probabilistic and occlusion-aware 3D Morphable Face Model adaptation framework following an Analysis-by-Synthesis setup. The key idea is to segment the image into regions explained by separate models. Our framework includes a 3D Morphable Face Model, a prototypebased beard model and a simple model for occlusions and background regions. The segmentation and all the model parameters have to be inferred from the single target image. Face model adaptation and segmentation are solved jointly using an expectation-maximizationlike procedure. During the E-step, we update the segmentation and in the M-step the face model parameters are updated. For face model adaptation we apply a stochastic sampling strategy based on the Metropolis-Hastings algorithm. For segmentation, we apply Loopy Belief Propagation for inference in a Markov random field. Illumination estimation is critical for occlusion handling. Our combined segmentation and model adaptation needs a proper initialization of the illumination parameters. We propose a RANSAC-based robust illumination estimation technique. By applying this method to a large face image database we obtain a first empirical distribution of real-world illumination conditions. The obtained empirical distribution is made publicly available and can be used as prior in probabilistic frameworks, for regularization or to synthesize data for deep learning methods.