We present new techniques for creating photorealistic textured 3D facial models from photographs of a human subject, and for creating smooth transitions between different facial e...
Frederic H. Pighin, Jamie Hecker, Dani Lischinski,...
We propose a novel formulation of stereo matching that considers each pixel as a feature vector. Under this view, matching two or more images can be cast as matching point clouds i...
Structured outputs such as multidimensional vectors or graphs are frequently encountered in real world pattern recognition applications such as computer vision, natural language pr...
We address the problem of efficiently estimating the rotation of a camera relative to the canonical 3D Cartesian frame of an urban scene, under the so-called "Manhattan World&...
Patrick Denis, James H. Elder, Francisco J. Estrad...
Abstract. Stereo matching is an ill-posed problem for at least two principal reasons: (1) because of the random nature of match similarity measure and (2) because of structural amb...