We present a new approach for the coarse segmentation of tubular structures in 3D image data. Our algorithm, which requires only few initial values and minimal user interaction, c...
We present a practical framework for detecting and modeling 3D static occlusions for wide-baseline, multi-camera scenarios where the number of cameras is small. The framework cons...
Current object class recognition systems typically target 2D bounding box localization, encouraged by benchmark data sets, such as Pascal VOC. While this seems suitable for the de...
Bojan Pepik, Michael Stark, Peter V. Gehler, Bernt...
In a previous paper we described a system which recursively recovers a super-resolved three dimensional surface model from a set of images of the surface. In that paper we assumed ...
Robin D. Morris, Vadim N. Smelyansky, Peter Cheese...
A method for matching sequences from two perspective views of a moving person silhouette is presented. Regular (approximate uniform thickness) parts are detected on an image and a ...