We formulate single-image multi-label segmentation into regions coherent in texture and color as a MAX-SUM problem for which efficient linear programming based solvers have recent...
Digital video applications exploit the intrinsic structure of video sequences. In order to obtain and represent this structure for video annotation and indexing tasks, the main ini...
Abstract This work proposes a system for the automatic construction of multi-spectral three-dimensional (3D) models of architecture. Besides the specific application, which concern...
Nicola Brusco, S. Capeleto, M. Fedel, A. Paviotti,...
Abstract--Image segmentation plays an important role in computer vision and image analysis. In this paper, image segmentation is formulated as a labeling problem under a probabilit...
Segmentation of video objects from background is a popular computer vision problem and has many important applications. Most existing methods are either computationally expensive ...