A model-based approach to reconstruction of 3D human arm motion from a monocular image sequence taken under orthographic projection is presented. The reconstruction is divided into...
This paper addresses the problem of recovering 3D non-rigid shape models from image sequences. For example, given a video recording of a talking person, we would like to estimate ...
Christoph Bregler, Aaron Hertzmann, Henning Bierma...
Abstract. In order to reconstruct 3-D Euclidean shape by the TomasiKanade factorization, one needs to specify an affine camera model such as orthographic, weak perspective, and par...
Ken-ichi Kanatani, Yasuyuki Sugaya, Hanno Ackerman...
This paper proposes a method of determining human head poses from a sequence of images. The main idea is to use some features in a 3D head model to generate a virtual fronto-paral...
—Matrix factorization methods are now widely used to recover 3D structure from 2D projections [1]. In practice, the observation matrix to be factored out has missing data, due to...