Many tasks in computer vision involve assigning a label (such as disparity) to every pixel. These tasks can be formulated as energy minimization problems. In this paper, we conside...
Abstract. We present a probabilistic algorithm for finding correspondences across multiple images. The algorithm runs in a distributed setting, where each camera is attached to a s...
We introduce several generalizations of classical computer science problems obtained by replacing simpler objective functions with general submodular functions. The new problems i...
Abstract. This paper presents an approach to object discovery in a given unlabeled image set, based on mining repetitive spatial configurations of image contours. Contours that si...
We propose an energy-based framework for approximating surfaces from a cloud of point measurements corrupted by noise and outliers. Our energy assigns a tangent plane to each (noi...