This paper describes a new technique for statistical 3{D object localization. Local feature vectors are extracted for all image positions, in contrast to segmentation in classical...
We propose a new approach for detecting low textured
planar objects and estimating their 3D pose. Standard
matching and pose estimation techniques often depend on
texture and fe...
Stefan Holzer, Stefan Hinterstoisser, Slobodan Ili...
Construction of key poses is one of the most tedious and time consuming steps in synthesizing of 3D virtual actors. Recent alternate schemes expect the user to specify two inputs. ...
Sculpting various 3D facial expressions from a static 3D face model is a process with intensive manual tuning efforts. In this paper, we present an interactive 3D facial expressio...
We advocate the use of Gaussian Process Dynamical Models (GPDMs) for learning human pose and motion priors for 3D people tracking. A GPDM provides a lowdimensional embedding of hu...