Sami Romdhani

A 3D Face Model for Pose and Illumination Invariant Face Recognition

Generative 3D face models are a powerful tool in computer vision. They provide pose and illumination invariance by modeling the space of 3D faces and the imaging process. The power of these models comes at the cost of an expensive and tedious construction process, which has led the community to focus on more easily constructed but less powerful models. With this paper we publish a generative 3D shape and texture model, the Basel Face Model (BFM), and demonstrate its application to several face recognition task. We improve on previous models by offering higher shape and texture accuracy due to a better scanning device and less correspondence artifacts due to an improved registration algorithm. The same 3D face model can be fit to 2D or 3D images acquired under different situations and with different sensors using an analysis by synthesis method. The resulting model parameters separate pose, lighting, imaging and identity parameters, which facilitates invariant face recognition across sensors and data sets by comparing only the identity parameters. We hope that the availability of this registered face model will spur research in generative models. Together with the model we publish a set of detailed recognition and reconstruction results on standard databases to allow complete algorithm comparisons.

Optimal Step Nonrigid ICP Algorithms for Surface Registration

We show how to extend the ICP framework to nonrigid registration, while retaining the convergence properties of the original algorithm. The resulting optimal step nonrigid ICP framework allows the use of different regularisations, as long as they have an adjustable stiffness parameter. The registration loops over a series of decreasing stiffness weights, and incrementally deforms the template towards the target, recovering the whole range of global and local deformations. To find the optimal deformation for a given stiffness, optimal iterative closest point steps are used. Preliminary correspondences are estimated by a nearest-point search. Then the optimal deformation of the template for these fixed correspondences and the active stiffness is calculated. Afterwards the process continues with new correspondences found by searching from the displaced template vertices. We present an algorithm using a locally affine regularisation which assigns an affine transformation to each vertex and minimises the difference in the transformation of neighbouring vertices. It is shown that for this regularisation the optimal deformation for fixed correspondences and fixed stiffness can be determined exactly and efficiently. The method succeeds for a wide range of initial conditions, and handles missing data robustly. It is compared qualitatively and quantitatively to other algorithms using synthetic examples and real world data.

Face identification across different poses and illuminations with a 3D morphable model

We present a novel approach for recognizing faces in images taken from different directions and under different illumination. The method is based on a 3D morphable face model that encodes shape and texture in terms of model parameters, and an algorithm that recovers these parameters from a single image of a face. For face identification, we use the shape and texture parameters of the model that are separated from imaging parameters, such as pose and illumination. In addition to the identity, the system provides a measure of confidence. We report experimental results for more than 4000 images from the publicly available CMU-PIE database.

Face Identification by Fitting a 3D Morphable Model Using Linear Shape and Texture Error Functions

This paper presents a novel algorithm aiming at analysis and identification of faces viewed from different poses and illumination conditions. Face analysis from a single image is performed by recovering the shape and textures parameters of a 3D Morphable Model in an analysis-by-synthesis fashion. The shape parameters are computed from a shape error estimated by optical flow and the texture parameters are obtained from a texture error. The algorithm uses linear equations to recover the shape and texture parameters irrespective of pose and lighting conditions of the face image. Identification experiments are reported on more than 5000 images from the publicly available CMU-PIE database which includes faces viewed from 13 different poses and under 22 different illuminations. Extensive identification results are available on our web page for future comparison with novel algorithms.

A Multi-View Nonlinear Active Shape Model Using Kernel PCA.

Recovering the shape of any 3D object using multiple 2D views requires establishing correspondence between feature points at different views. However changes in viewpoint introduce self-occlusions, resulting nonlinear variations in the shape and inconsistent 2D features between views. Here we introduce a multi-view nonlinear shape model utilising 2D view-dependent constraint without explicit reference to 3D structures. For nonlinear model transformation, we adopt Kernel PCA based on Support Vector Machines.

Estimating 3D shape and texture using pixel intensity, edges, specular highlights, texture constraints and a prior

We present a novel algorithm aiming to estimate the 3D shape, the texture of a human face, along with the 3D pose and the light direction from a single photograph by recovering the parameters of a 3D morphable model. Generally, the algorithms tackling the problem of 3D shape estimation from image data use only the pixels intensity as input to drive the estimation process. This was previously achieved using either a simple model, such as the Lambertian reflectance model, leading to a linear fitting algorithm. Alternatively, this problem was addressed using a more precise model and minimizing a non-convex cost function with many local minima. One way to reduce the local minima problem is to use a stochastic optimization algorithm. However, the convergence properties (such as the radius of convergence) of such algorithms, are limited. Here, as well as the pixel intensity, we use various image features such as the edges or the location of the specular highlights. The 3D shape, texture and imaging parameters are then estimated by maximizing the posterior of the parameters given these image features. The overall cost function obtained is smoother and, hence, a stochastic optimization algorithm is not needed to avoid the local minima problem. This leads to the multi-features fitting algorithm that has a wider radius of convergence and a higher level of precision. This is shown on some example photographs, and on a recognition experiment performed on the CMU-PIE image database.

Face Recognition Using 3-D Models: Pose and Illumination

Unconstrained illumination and pose variation lead to significant variation in the photographs of faces and constitute a major hurdle preventing the widespread use of face recognition systems. The challenge is to generalize from a limited number of images of an individual to a broad range of conditions. Recently, advances in modeling the effects of illumination and pose have been accomplished using three-dimensional (3-D) shape information coupled with reflectance models. Notable developments in understanding the effects of illumination include the nonexistence of illumination invariants, a characterization of the set of images of objects in fixed pose under variable illumination (the illumination cone), and the introduction of spherical harmonics and low-dimensional linear subspaces for modeling illumination. To generalize to novel conditions, either multiple images must be available to reconstruct 3-D shape or, if only a single image is accessible, prior information about the 3-D shape and appearance of faces in general must be used. The 3-D Morphable Model was introduced as a generative model to predict the appearances of an individual while using a statistical prior on shape and texture allowing its parameters to be estimated from single image. Based on these new understandings, face recognition algorithms have been developed to address the joint challenges of pose and lighting. In this paper, we review these developments and provide a brief survey of the resulting face recognition algorithms and their performance

Reconstructing High Quality Face-Surfaces using Model Based Stereo

We present a novel model based stereo system, which accurately extracts the 3D shape and pose of faces from multiple images taken simultaneously. Extracting the 3D shape from images is important in areas such as pose-invariant face recognition and image manipulation. The method is based on a 3D morphable face model learned from a database of facial scans. The use of a strong face prior allows us to extract high precision surfaces from stereo data of faces, where traditional correlation based stereo methods fail because of the mostly textureless input images. The method uses two or more uncalibrated images of arbitrary baseline, estimating calibration and shape simultaneously. Results using two and three input images are presented. We replace the lighting and albedo estimation of a monocular method with the use of stereo information, making the system more accurate and robust. We evaluate the method using ground truth data and the standard PIE image dataset. A comparison with the state of the art monocular system shows that the new method has a significantly higher accuracy.

Efficient Face Detection by a Cascaded Support Vector Machine Using Haar-Like Features

In this paper, we present a novel method for reducing the computational complexity of a Support Vector Machine (SVM) classifier without significant loss of accuracy. We apply this algorithm to the problem of face detection in images. To achieve high run-time efficiency, the complexity of the classifier is made dependent on the input image patch by use of a Cascaded Reduced Set Vector expansion of the SVM. The novelty of the algorithm is that the Reduced Set Vectors have a Haar-like structure enabling a very fast SVM kernel evaluation by use of the Integral Image. It is shown in the experiments that this novel algorithm provides, for a comparable accuracy, a 200 fold speed-up over the SVM and an 6 fold speed-up over the Cascaded Reduced Set Vector Machine.

Combining PCA and LFA for Surface Reconstruction from a Sparse Set of Control Points

This paper presents a novel method for 3D surface reconstruction based on a sparse set of 3D control points. For object classes such as human heads, prior information about the class is used in order to constrain the results. A common strategy to represent object classes for a reconstruction application is to build holistic models, such as PCA models. Using holistic models involves a trade-off between reconstruction of the measured points and plausibility of the result. We introduce a novel object representation that provides local adaptation of the surface, able to fit 3D control points exactly without affecting areas of the surface distant from the control points. The method is based on an interpolation scheme, opposed to approximation schemes generally used for surface reconstruction. Our interpolation method reduces the Euclidean distance between a reconstruction and its ground truth while preserving its smoothness and increasing its perceptual quality