Statistical shape-and-texture appearance models employ image metamorphosis to form a rich, compact representation of object appearance. They achieve their efficiency by decomposin...
Mean shift is a popular method to segment images and videos. Pixels are represented by feature points, and the segmentation is driven by the point density in feature space. In thi...
We present variable-aperture photography, a new method for analyzing sets of images captured with different aperture settings, with all other camera parameters fixed. We show that...
In this paper, we propose a method to incrementally superresolve 3D facial texture by integrating information frame by frame from a video captured under changing poses and illumin...
Jiangang Yu, Bir Bhanu, Yilei Xu, Amit K. Roy Chow...
We present a novel framework for characterizing signals in images using techniques from computational algebraic topology. This technique is general enough for dealing with noisy mu...