Abstract : We will describe our ongoing work on learning-based methods for recovering 3D human body pose and motion from single images and from monocular image sequences. The methods work directly with raw image observations and require neither an explicit 3D body model nor a prior labelling of body parts in the image.
https://hal.inria.fr/inria-00548548
Contributeur : Thoth Team
<>
Soumis le : lundi 20 décembre 2010 - 09:09:36
Dernière modification le : mercredi 11 avril 2018 - 01:54:25
Document(s) archivé(s) le : lundi 21 mars 2011 - 03:15:13
Ankur Agarwal, Bill Triggs. Learning to Recover 3D Human Pose from Silhouettes. Yann LeCun and Yoshua Bengio. Learning 2004 - Abstracts of the 2004 Snowbird Learning Workshop, Apr 2004, Snowbird, United States. 2004. 〈inria-00548548〉
