Abstract. We recently introduced the watershed cuts, a notion of watershed in edge-weighted graphs. In this paper, we propose a new thinning paradigm to compute them. More precisel...
Jean Cousty, Gilles Bertrand, Laurent Najman, Mich...
We propose a new method to unmix hyperspectral images. Our method exploits the structure of the material abundance maps by assuming that in some regions of the spatial dimension, ...
The (decisional) learning with errors problem (LWE) asks to distinguish “noisy” inner products of a secret vector with random vectors from uniform. In recent years, the LWE pro...
A popular approach to pixel labeling problems, such as multiclass image segmentation, is to construct a pairwise conditional Markov random field (CRF) over image pixels where the...
We present a new feature based algorithm for stereo correspondence. Most of the previous feature based methods match sparse features like edge pixels, producing only sparse dispar...