Most methods for object class segmentation are formulated as a labelling problem over a single choice of quantisation of an image space - pixels, segments or group of segments. It...
Lubor Ladicky, Christopher Russell, Pushmeet Kohli...
In this paper we propose a novel framework for efficiently extracting foreground objects in so called shortbaseline image sequences. We apply the obtained segmentation to improve...
We propose a novel step toward the unsupervised segmentation of whole objects by combining "hints" of partial scene segmentation offered by multiple soft, binary mattes....
Andrew N. Stein, Thomas S. Stepleton, Martial Hebe...
Segmentation of range images has long been considered an important and difficult problem and continues to attract the attention of researchers in computer vision. In this paper we...
A key problem in learning multiple objects from unlabeled images is that it is a priori impossible to tell which part of the image corresponds to each individual object, and which...