We present a method for learning appearance models that can be used to recognise and track both 3D head pose and identities of novel subjects with continuous head movement across ...
Skeletal animation with vertex blending is a popular method to model believable 3D characters. Its main advantage is its speed that allows real-time deformation even on low-level ...
We are investigating methods to accelerate rendering of architectural walkthroughs. In this paper, we improve upon a cells and portals framework by using images to replace geometr...
Matthew M. Rafferty, Daniel G. Aliaga, Voicu Popes...
We present a Bayesian approach to image-based visual hull reconstruction. The 3-D shape of an object of a known class is represented by sets of silhouette views simultaneously obs...
Kristen Grauman, Gregory Shakhnarovich, Trevor Dar...
Recovering the 3D coordinates of various joints of the human body from an image is a critical first step for several model-based human tracking and optical motion capture systems....