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...
We examine the performance of phase-based and energybased techniques for estimating image orientation, emphasizing measurement stability under deformations that commonly occur in ...
This paper proposes a “non-contact virtual clay modeling interface.” We developed a prototype of a three-dimensional modeling system that allows the user to deform the “virt...
Tree-structured models have been widely used for human pose estimation, in either 2D or 3D. While such models allow efficient learning and inference, they fail to capture additiona...
A novel method for the segmentation of multiple objects from 3D medical images using inter-object constraints is presented. Our method is motivated by the observation that neighbor...