Douglas DeCarlo

An anthropometric face model using variational techniques

We describe a system that automatically generates varied geometric models of human faces. A collection of random measurements of the face is generated according to anthropometric statistics for likely face measurements in a population. These measurements are then treated as constraints on a parameterized surface. Variational modeling is used to find a smooth surface that satisfies these constraints while using a prototype shape as a reference.

The integration of optical flow and deformable models with applications to human face shape and motion estimation

We present a formal methodology for the integration of optical flow and deformable models. The optical flow constraint equation provides a non-holonomic constraint on the motion of the deformable model. In this augmented system, forces computed from edges and optical flow are used simultaneously. When this dynamic system is solved, a model-based least-squares solution for the optical flow is obtained and improved estimation results are achieved. The use of a 3-D model reduces or eliminates problems associated with optical flow computation. This approach instantiates a general methodology for treating visual cues as constraints on deformable models. We apply this framework to human face shape and motion estimation. Our 3-D deformable face model uses a small number of parameters to describe a rich variety of face shapes and facial expressions. We present experiments in extracting the shape and motion of a face from image sequences.

Deformable model-based shape and motion analysis from images using motion residual error

We present a novel method for the shape and motion estimation of a deformable model using error residuals from model-based motion analysis. The motion of the model is first estimated using a model-based least squares method. Using the residuals from the least squares solution, the non-rigid structure of the model can be better estimated by computing how changes in the shape of the model affect its motion parameterization. This method is implemented as a component in a deformable model-based framework that uses optical flow information and edges. This general model-based framework is applied to human face shape and motion estimation. We present experiments that demonstrate that this framework is a considerable improvement over a framework that uses only optical flow information and edges.

Blended deformable models

This paper develops a new class of parameterized models based on the linear interpolation of two parameterized shapes along their main axes, using a blending function. This blending function specifies the relative contribution of each component shape on the resulting blended shape. The resulting blended shape can have aspects of each of the component shapes. Using a small number of additional parameters, blending extends the coverage of shape primitives while also providing abstraction of shape. In particular, it offers the ability to construct shapes whose genus can change. Blended models are incorporated into a physics-based shape estimation framework which uses dynamic deformable models. Finally, we present experiments involving the extraction of complex shapes from range data including examples of dynamic genus change.

Adaptive shape evolution using blending

We propose a shape representation scheme which allows two shapes to be combined into a single model. The desired regions of the two shapes are selected, and then merged together forming a blended shape. For reconstruction, blending is incorporated into a deformable model framework. The model automatically adapts to the data, blending when necessary. Hierarchical blending allows multiple blends of a shape to occur forming an evolution from the initial shape of a sphere to the final shape. Blending also allows the insertion of a hole between arbitrary locations. The models used are globally defined, making the recovered shape a natural symbolic description. We present reconstruction experiments involving shapes of various topologies.<<ETX>>

Deformable model-based face shape and motion estimation

We describe a model-based approach to human face shape and motion estimation using a deformable model framework in which optical flow information has been integrated. Our 3-D deformable face model uses a small number of parameters to describe a rich variety of face shapes and facial expressions. A detailed face model allows for the handling of self-occlusion and the correction of error accumulation in tracking by aligning the expected location of face features with those found in the input images. We present experiments in which we employ Kalman filtering to estimate the shape and motion of a face from image sequences of four subjects. The face is successfully tracked even in the presence of large head rotations.

Reverse engineering using blending and adaptive shape evolution

We propose a method for reverse engineering that is based on the use of topologically adaptive deformable models. The technique is based on a shape representation scheme which allows two shapes to be combined into a single model. The desired regions of the two shapes are selected, and then merged together forming a blended shape. For reconstruction, blending is incorporated into a deformable model framework. The model automatically adapts to the data, blending when necessary. Hierarchical blending allows multiple blends of a shape to occur, forming an evolution from the initial shape of a sphere to the final shape. Blending also allows the insertion of a hole between arbitrary locations. The models used are globally defined, making the recovered shape a natural symbolic description. We present reconstruction experiments involving shapes of various topologies.