In video post-production it is often necessary to track interest points in the video. This is called off-line tracking, because the complete video is available to the algorithm and can be contrasted with on-line tracking, where an incoming stream is tracked in real time. Off-line tracking should be accurate and - if used interactively - needs to be fast, preferably faster than real-time. We describe a 50 to 100 frames per second off-line tracking algorithm, which globally maximizes the probability of the track given the complete video. The algorithm is more reliable than previous methods because it explains the complete frames, not only the patches of the final track, making as much use of the data as possible. It achieves efficiency by using a greedy search strategy with deferred cost evaluation, focusing the computational effort on the most promising track candidates while finding the globally optimal track.

Fitting statistical 2D and 3D shape models to images is necessary for a variety of tasks, such as video editing and face recognition. Much progress has been made on local fitting from an initial guess, but determining a close enough initial guess is still an open problem. One approach is to detect distinct landmarks in the image and initalize the model fit from these correspondences. This is difficult, because detection of landmarks based only on the local appearance is inherently ambiguous. This makes it necessary to use global shape information for the detections. We propose a method to solve the combinatorial problem of selecting out of a large number of candidate landmark detections the configuration which is best supported by a shape model. Our method, as opposed to previous approaches, always finds the globally optimal configuration. The algorithm can be applied to a very general class of shape models and is independent of the underlying feature point detector. Its theoretic optimality is shown, and it is evaluated on a large face dataset.

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.

Efficient and accurate fitting of active appearance models (AAM) is a key requirement for many applications. The most efficient fitting algorithm today is inverse compositional image alignment (ICIA). While ICIA is extremely fast, it is also known to have a small convergence radius. Convergence is especially bad when training and testing images differ strongly, as in multi-person AAMs. We describe “forward” compositional image alignment in a consistent framework which also incorporates methods previously termed “inverse” compositional, and use it to develop two novel fitting methods. The first method, compositional gradient descent (CoDe), is approximately four times slower than ICIA, while having a convergence radius which is even larger than that achievable by direct quasi-Newton descent. An intermediate convergence range with the same speed as ICIA is achieved by LinCoDe, the second new method. The success rate of the novel methods is 10 to 20 times higher than that of the original ICIA method.

We describe an expression-invariant method for face recognition by fitting an identity/expression separated 3D Morphable Model to shape data. The expression model greatly improves recognition and retrieval rates in the uncooperative setting, while achieving recognition rates on par with the best recognition algorithms in the face recognition great vendor test. The fitting is performed with a robust nonrigid ICP algorithm. It is able to perform face recognition in a fully automated scenario and on noisy data. The system was evaluated on two datasets, one with a high noise level and strong expressions, and the standard UND range scan database, showing that while expression invariance increases recognition and retrieval performance for the expression dataset, it does not decrease performance on the neutral dataset. The high recognition rates are achieved even with a purely shape based method, without taking image data into account.

We present a method for face recognition by fitting a 3D Morphable Model to shape data. Fitting is done with a a robust nonrigid ICP algorithm. For recognition, it is possible to use either the fitted model parameters, or the correspondences induced by the model. We compare different similarity measures, and show that a 3D Morphable Model allows very robust retrieval results.

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.

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.