Event Location: NSH 1507
Bio: Xue Bai is a Ph.D. student of Prof. Guillermo Sapiro, in Electrical and Computer Engineering, University of Minnesota.

Abstract: Digital image/video segmentation and matting is one of the most fundamental and challenging problems in computer vision and graphics. One popular application, as in many movie special effects, is to extract the foreground object out of the background scene, and composite it onto a new background with minimal visual artifacts.

We developed several efficient object cutout systems with the state-of-the-art performance. The first one is an interactive framework for soft segmentation based on weighted geodesic distances, which runs with linear time complexity. The second system, Roto Brush, was designed to meet the standards of the professional video production community. In this system segmentation is achieved by the collaboration of a set of local classifiers that adaptively integrate multiple local features. Another framework, Dynamic Color Flow, is introduced for more accurate color modeling in complicated videos. Numerous examples as well as live demos will be presented in the talk.