Abstract— Navigating through unknown outdoor environments requires a robot to be able to see and model the far field terrain. In recent years this problem of seeing beyond relia...
Much of the research on video-based human motion capture assumes the body shape is known a priori and is represented coarsely (e.g. using cylinders or superquadrics to model limbs...
Alexandru O. Balan, Leonid Sigal, Michael J. Black...
We present a method for obtaining quantitative images from dual energy X-ray CT measurements. We adopt a statistical model for the data and reconstruct images by maximizing the lo...
Joseph A. O'Sullivan, Jasenka Benac, Jeffrey F. Wi...
Abstract. An unsupervised model-based strategy for bias field correction is proposed. We assume that information (in the sense of the information theory) in the corrupted image is...
Abstract. Figure/ground assignment is a key step in perceptual organization which assigns contours to one of the two abutting regions, providing information about occlusion and all...