We describe an approach to category-level detection and viewpoint estimation for rigid 3D objects from single 2D images. In contrast to many existing methods, we directly integrat...
Daniel Glasner, Meirav Galun, Sharon Alpert, Ronen...
We describe a method for recovering 3D human body pose from silhouettes. Our model is based on learning a latent space using the Gaussian Process Latent Variable Model (GP-LVM) [1]...
Carl Henrik Ek, Philip H. S. Torr, Neil D. Lawrenc...
We present a 3D, probabilistic object-surface model, along with mechanisms for probabilistically integrating unregistered 2.5D views into the model, and for segmenting model instan...
Pose space deformation generalizes and improves upon both shape interpolation and common skeleton-driven deformation techniques. This deformation approach proceeds from the observ...
We consider the problem of recovering a matrix from its action on a known vector in the setting where the matrix can be represented efficiently in a known matrix dictionary. Conne...