Carregant...
Carregant...

Vés al contingut (premeu Retorn)

Combining local-physical and global-statistical models for sequential deformable shape from motion

Autor
Agudo, A.; Moreno-Noguer, F.
Tipus d'activitat
Article en revista
Revista
International journal of computer vision
Data de publicació
2017-04-01
Volum
122
Número
2
Pàgina inicial
371
Pàgina final
387
DOI
https://doi.org/10.1007/s11263-016-0972-8 Obrir en finestra nova
Projecte finançador
VISEN ,CHIST-ERA CALL 2011
Repositori
http://hdl.handle.net/2117/108518 Obrir en finestra nova
URL
https://link.springer.com/article/10.1007%2Fs11263-016-0972-8 Obrir en finestra nova
Resum
In this paper, we simultaneously estimate camera pose and non-rigid 3D shape from a monocular video, using a sequential solution that combines local and global representations. We model the object as an ensemble of particles, each ruled by the linear equation of the Newton's second law of motion. This dynamic model is incorporated into a bundle adjustment framework, in combination with simple regularization components that ensure temporal and spatial consistency. The resulting approach allows to...
Citació
Agudo, A., Moreno-Noguer, F. Combining local-physical and global-statistical models for sequential deformable shape from motion. "International journal of computer vision", 1 Abril 2017, vol. 122, núm. 2, p. 371-387.
Paraules clau
Bundle adjustment, Low-rank models, Particle dynamics, Sequential non-rigid structure from motion
Grup de recerca
ROBiri - Grup de Robòtica de l'IRI