Image matting is of great importance in both computer vision and graphics applications. Most existing state-of-the-art techniques rely on large sparse matrices such as the matting ...
To detect multiple objects of interest, the methods based on Hough transform use non-maxima supression or mode seeking in order to locate and to distinguish peaks in Hough images....
This paper presents a method for rectifying video sequences from rolling shutter (RS) cameras. In contrast to previous RS rectification attempts we model distortions as being cau...
We present an interactive approach for segmenting thin volumetric structures. The proposed segmentation model is based on an anisotropic weighted Total Variation energy with a glob...
Christian Reinbacher, Thomas Pock, Christian Bauer...
Most existing structure-from-motion methods follow a common two-step scheme, where relative camera motions are estimated in the first step and 3D structure is computed afterward ...