We propose a new template-based approach for viewinvariant recognition of body poses, based on geometric constraints derived from the motion of body point triplets. In addition to...
We address the problem of estimating human pose in video sequences, where rough location has been determined. We exploit both appearance and motion information by defining suitabl...
Retargeting and interpolation methods may introduce physical inaccuracies in virtual human animation. This paper presents a method for evaluating the dynamical correctness of reta...
Based on scaling laws describing the statistical structure
of turbulent motion across scales, we propose a multiscale
and non-parametric regularizer for optic-flow estimation.
R...
Patrick H´eas, Etienne M´emin, Dominique Heitz, ...
This paper presents a method to capture human motion from silhouettes of a person in multi-view video streams. Applying a hierarchical kinematic body model motion parameters are e...
Christian Theobalt, Joel Carranza, Marcus A. Magno...