Texturing using a set of two dimensional image maps is an established and widespread practice. However, it has many limitations. Parameterizing a model in texture space can be ver...
This paper proposes the use of feature tracks for the detection of concepts in video, particularly dynamic concepts. Feature tracks are defined as sets of local interest points fo...
Vasileios Mezaris, Anastasios Dimou, Ioannis Kompa...
We present a multiresolution framework, called Multi-Tetra framework, that approximates volume data with different levelsof-detail tetrahedra. The framework is generated through a...
We present a variational approachto dense stereo reconstructionwhich combines powerful tools such as regularization and multi-scale processing to estimate directly depth from a num...
Scale-space representation of an image is a significant way to generate features for classification. However, for a specific classification task, the entire scale-space may not be...