Mathematics Colloquia and Seminars

Return to Colloquia & Seminar listing

I will describe a class of robust nonparametric estimation methods which are ideally suited for the reconstruction of multidimensional signals from noise-corrupted and sparse or irregularly sampled data. The framework results in locally adapted kernels which take into account both the spatial density of the available samples, and the actual values of those samples. As such, they are automatically steered and adapted to both the given sampling "geometry", and the samples' "radiometry". As the framework we propose does not rely upon strong assumptions about noise or sampling distributions, it is applicable to a wide variety of problems, including image and video upscaling and superresolution, high quality multidimensional interpolation from irregular, sparse and noisy samples, image and video denoising, and deblurring. Interestingly, in many of the diverse applications mentioned above, the resulting algorithms yield performance that is at or near the state of the art. \n Biography: Peyman Milanfar received the B.S. degree in Electrical Engineering/Mathematics from the University of California, Berkeley, and the S.M. and Ph.D. degrees in Electrical Engineering from the Massachusetts Institute of Technology. Until 1999, he was a Senior Research Engineer at SRI International, Menlo Park, CA. He is currently Professor of Electrical Engineering at the University of California, Santa Cruz. He was a Consulting Assistant Professor of computer science at Stanford University from 1998-2000, and a visiting Associate Professor there in 2002. His technical interests are in statistical signal and image processing, and inverse problems. He won a National Science Foundation CAREER award in 2000. He is associate editor for IEEE Transactions on Image Processing and was associate editor for the IEEE Signal Processing Letters from 1998 to 2001. He is a Senior member of the IEEE.