Abstract. This paper presents a new framework for analyzing the geometry of multiple 3D scene points from multiple uncalibrated images, based on decomposing the projection of these...
Helmholtz stereovision methods are limited to binocular stereovision or depth maps reconstruction. In this paper, we extend these methods to recover the full 3D shape of the object...
We present an algorithm for jointly learning a consistent bidirectional generative-recognition model that combines top-down and bottom-up processing for monocular 3d human motion ...
Cristian Sminchisescu, Atul Kanaujia, Dimitris N. ...
In this paper we present a novel integrated 3D editing environment that combines recent advantages in various fields of computer graphics, such as shape modelling, video-based Hum...
Gerhard H. Bendels, Ferenc Kahlesz, Reinhard Klein
This paper presents a 3D face photography system based on a small set of training facial range images. The training set is composed by 2D texture and 3D range images (i.e. geometr...
Jesus P. Mena-Chalco, Ives Macedo, Luiz Velho, Rob...