A Markov Random Field (MRF) based local stereo matching algorithm that estimates parameters automatically from statistics is proposed. For an iterative optimization, cost functions working on local support neighborhood are developed. Data model parameters are pre-estimated from one of the stereo images by applying a noise equivalence hypothesis. The smoothness model parameters are estimated with maximum likelihood (ML) applying disparity gradient constraint and 3*sigma confidence boundary. The confidence boundary also defines the parameters for handling discontinuities in data and smoothness. Additionally, homogeneous points are included into the support neighborhood to achieve high matching rate along surface borders. Finally, a pair of cost functions is modeled to match the images symmetrically for improved matching. Experiments on ground truth datasets show that among the existing algorithms with statistical estimation of the parameters, the proposed algorithm delivers the highest matching rate.

This paper describes an approach to reformulating the stereo matching problem as a large scale Linear Program.
The approach proceeds by approximating the match cost function associated with each pixel with a piecewise linear convex function. Regularization terms related to the first and second derivative of the disparity field are also captured with piecewise linear penalty terms. The resulting large scale linear program can be tackled using interior point methods and the associated Newton steps involve Hessian matrices that reflect the structure of the underlying pixel grid. The proposed scheme effectively exploits this structure to efficiently solve the large scale global optimization problem.

We explore a new approach to marker-less motion tracking of a priori known skinned meshes using both optical flow and silhouette information. We present a formulation which considers in a unified way both these two kinds of information and accounts for the non-rigid deformations of the object skin modeling them using the Skeletal Subspace Deformation (SSD). We then demonstrate the effectiveness of our technique showing its performance in a four camera set-up tracking a subject modeled by a skeleton with 46 degrees of freedom.