Kristina Scherbaum

Exchanging Faces in Images

Pasting somebodys face into an existing image with traditional photo retouching and digital image processing tools has only been possible if both images show the face from the same viewpoint and with the same illumination. However, this is rarely the case for given pairs of images. We present a system that exchanges faces across large differences in viewpoint and illumination. It is based on an algorithm that estimates 3D shape and texture along with all relevant scene parameters, such as pose and lighting, from single images. Manual interaction is reduced to clicking on a set of about 7 feature points, and marking the hairline in the target image. The system can be used for image processing, virtual try‐on of hairstyles, and face recognition. By separating face identity from imaging conditions, our approach provides an abstract representation of images and a novel, high‐level tool for image manipulation.

Fitting a Morphable Model to 3D Scans of Faces

This paper presents a top-down approach to 3D data analysis by fitting a morphable model to scans of faces. In a unified framework, the algorithm optimizes shape, texture, pose and illumination simultaneously. The algorithm can be used as a core component in face recognition from scans. In an analysis-by-synthesis approach, raw scans are transformed into a PCA-based representation that is robust with respect to changes in pose and illumination. Illumination conditions are estimated in an explicit simulation that involves specular and diffuse components. The algorithm inverts the effect of shading in order to obtain the diffuse reflectance in each point of the facial surface. Our results include illumination correction, surface completion and face recognition on the FRGC database of scans.

Prediction of Individual Non-Linear Aging Trajectories of Faces

Represented in a Morphable Model, 3D faces follow curved trajectories in face space as they age. We present a novel algorithm that computes the individual aging trajectories for given faces, based on a non‐linear function that assigns an age to each face vector. This function is learned from a database of 3D scans of teenagers and adults using support vector regression.

Computer‐Suggested Facial Makeup

Finding the best makeup for a given human face is an art in its own right. Experienced makeup artists train for years to be skilled enough to propose a best‐fit makeup for an individual. In this work we propose a system that automates this task. We acquired the appearance of 56 human faces, both without and with professional makeup. To this end, we use a controlled‐light setup, which allows to capture detailed facial appearance information, such as diffuse reflectance, normals, subsurface‐scattering, specularity, or glossiness. A 3D morphable face model is used to obtain 3D positional information and to register all faces into a common parameterization. We then define makeup to be the change of facial appearance and use the acquired database to find a mapping from the space of human facial appearance to makeup. Our main application is to use this mapping to suggest the best‐fit makeup for novel faces that are not in the database. Further applications are makeup transfer, automatic rating of makeup, makeup‐training, or makeup‐exaggeration. As our makeup representation captures a change in reflectance and scattering, it allows us to synthesize faces with makeup in novel 3D views and novel lighting with high realism. The effectiveness of our approach is further validated in a user‐study.

Rapid stereo-vision enhanced face detection

This paper presents a real-time face detection algorithm. It improves state-of-the-art 2D object detection techniques by additionally evaluating a disparity map, which is estimated for the face region using a calibrated stereo camera setup. First, faces are detected in the 2D images with a rapid object classifier based on haar-like features. In a second step, falsely detected faces are removed by analyzing the disparity map. In the near field of the camera, a classifier is used, which evaluates the Eigenfaces of the normalized disparity map. Thereby, the transformation into Eigenspace is learned off-line using a principal component analysis approach. In the far field, a much simpler approach determines false-positives by evaluating the relationship between the size of the face in the image and its distance to the camera. This novel combination of algorithms runs in real-time and significantly reduces the number of false-positives compared to classical 2D face detection approaches.

Data driven analysis of faces from images

This thesis proposes three new data-driven approaches to detect, analyze, or modify faces in images. All presented contributions are inspired by the use of prior knowledge and they derive information about facial appearances from pre-collected databases of images or 3D face models. First, we contribute an approach that extends a widely-used monocular face detector by an additional classifier that evaluates disparity maps of a passive stereo camera. The algorithm runs in real-time and significantly reduces the number of false positives compared to the monocular approach. Next, with a many-core implementation of the detector, we train view-dependent face detectors based on tailored views which guarantee that the statistical variability is fully covered. These detectors are superior to the state of the art on a challenging dataset and can be trained in an automated procedure. Finally, we contribute a model describing the relation of facial appearance and makeup. The approach extracts makeup from before/after images of faces and allows to modify faces in images. Applications such as machine-suggested makeup can improve perceived attractiveness as shown in a perceptual study. In summary, the presented methods help improve the outcome of face detection algorithms, ease and automate their training procedures and the modification of faces in images. Moreover, their data-driven nature enables new and powerful applications arising from the use of prior knowledge and statistical analyses.