The RKLT is a lossless approximation to the KLT, and has been recently employed for progressive lossy-to-lossless coding of hyperspectral images. Both yield very good coding perfo...
In this paper we revisit local feature detectors/descriptors developed for 2D images and extend them to the more general framework of scalar fields defined on 2D manifolds. We pro...
Andrei Zaharescu (INRIA Grenoble), Edmond Boyer (L...
A method for detecting and segmenting periodic motion is presented. We exploit periodicity as a cue and detect periodic motion in complex scenes where common methods for motion se...
We present a novel framework to exert topology control over a level set evolution. Level set methods offer several advantages over parametric active contours, in particular automat...
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...