We areinterestedin descriptionsof 3-D data sets,as obtained from stereoor a 3-D digitizer. We thereforeconsideras inputa sparsesetof points, possibly associated with certain orien...
This paper generalizes Markov Random Field (MRF) stereo methods to the generation of surface relief (height) fields rather than disparity or depth maps. This generalization enable...
George Vogiatzis, Philip H. S. Torr, Steven M. Sei...
Modeling representations of image patches that are quasi-invariant to spatial deformations is an important problem in computer vision. In this paper, we propose a novel concept, t...
Jan Ernst, Maneesh Kumar Singh, Visvanathan Ramesh
In this paper, we suggest to use a steepest descent algorithm for learning a parametric dictionary in which the structure or atom functions are known in advance. The structure of ...
Mahdi Ataee, Hadi Zayyani, Massoud Babaie-Zadeh, C...
We propose a novel clustering scheme for spatio-temporal segmentation of sparse motion fields obtained from feature tracking. The approach allows for the segmentation of meaningfu...