אירועים והרצאות בפקולטה למדעי המחשב ע"ש הנרי ומרילין טאוב

One of the most important aspects of solving a problem is that of choosing an appropriate parameterization. This trivial observation can be seen in many forms in image processing and computer vision. Global parametrizations include the Hough and Fourier transforms, whereas local parameterizations include sparsity-based patch models and over-parameterized approaches. My research explores important cases in motion analysis and 3D reconstruction where a careful choice of the parameterization matters. It leads, in these cases, to simple and yet generic formulations that can be efficiently implemented. The first part of my talk relates to 3D motion understanding, where I reformulate articulated motion as edge-preserving smoothing of Lie-group- valued images. The resulting generic algorithm obtains results comparable to those of domain specific tools, on 3D range data, at real-time speeds. Furthermore, it applies also to other inverse problems such as diffusion tensor imaging reconstruction, and direction diffusion. In the second part I show how structured light reconstruction can be formulated as probability maximization with respect to the range image. This allows us to incorporate sparse priors for the surface into the non-linear reconstruction process itself. These priors, resulting from the data, have a natural and intuitive interpretation. Furthermore, they help us obtain 3D reconstruction that is robust to low sensor exposure and motion artifacts.