- In multiview video coding, disparity compensated prediction exploits the correlation among different views. A common approach is to use the conventional motion compensated predic...
We present a novel approach to simultaneously reconstruct the 3D structure of a non-rigid coronary tree and estimate point correspondences between an input X-ray image and a refer...
Eduard Serradell (Institut de Robotica i Informati...
Co-segmentation is defined as jointly partitioning multiple images depicting the same or similar object, into foreground and background. Our method consists of a multiplescale mu...
This paper presents a method for learning 3D object templates from view labeled object images. The 3D template is defined in a joint appearance and geometry space, and is compose...
We propose a novel linear method for scale invariant figure ground separation in images and videos. Figure ground separation is treated as a superpixel labeling problem. We optim...