Structure and motion estimation from long image sequences is a an important and difficult problem in computer vision. We propose a novel approach based on nonlinear and adaptive ...
Video-rate registered range and intensity data are at reach of current sensor technology. This wealth of data can be pro tably exploited in order to estimate rigid motion paramete...
Luca Lucchese, Gianfranco Doretto, Guido M. Cortel...
This paper describes a data-driven approach for generating photorealistic animations of human motion. Each animation sequence follows a user-choreographed path and plays continuou...
Matthew Flagg, Atsushi Nakazawa, Qiushuang Zhang, ...
This paper describes a novel approach to 3D motion estimation of planar objects based on eigennormalization, Expansion Matching (EXM) and a scaled orthographic projection model. O...
The problem of multibody motion segmentation is an important and challenging issue in computer vision. In this paper, a novel segmentation technique based on simulated annealing (...