We present a novel approach to the problem of hairstyle construction from raw surface data such as the ones obtained from surface scans. Our approach is based on a shape matching ...
Gerrit Sobottka, Michael Kusak, Andreas Weber 0004
Methods based on local, viewpoint invariant features have proven capable of recognizing objects in spite of viewpoint changes, occlusion and clutter. However, these approaches fail...
Vittorio Ferrari, Tinne Tuytelaars, Luc J. Van Goo...
In this paper we propose a weakly supervised learning algorithm for appearance models based on the minimum description length (MDL) principle. From a set of training images or volu...
Georg Langs, Rene Donner, Philipp Peloschek, Horst...
Image segmentation techniques are predominately based on parameter-laden optimization processes. The segmentation objective function traditionally involves parameters (i.e. weights...
This paper addresses variational supervised texture segmentation. The main contributions are twofold. First, the proposed method circumvents a major problem related to classical t...