Carregant...
Carregant...

Vés al contingut (premeu Retorn)

Spatiotemporal descriptor for wide-baseline stereo reconstruction of non-rigid and ambiguous scenes

Autor
Trulls, E.; Sanfeliu, A.; Moreno-Noguer, F.
Tipus d'activitat
Presentació treball a congrés
Nom de l'edició
12th European Conference on Computer Vision
Any de l'edició
2012
Data de presentació
2012
Llibre d'actes
Computer vision - ECCV 2012: 12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012: proceedings
Pàgina inicial
441
Pàgina final
454
Editor
Springer
DOI
https://doi.org/10.1007/978-3-642-33712-3_32 Obrir en finestra nova
Repositori
http://hdl.handle.net/2117/19254 Obrir en finestra nova
Resum
This paper studies the use of temporal consistency to match appearance descriptors and handle complex ambiguities when computing dynamic depth maps from stereo. Previous attempts have designed 3D descriptors over the spacetime volume and have been mostly used for monocular action recognition, as they cannot deal with perspective changes. Our approach is based on a state-of-the-art 2D dense appearance descriptor which we extend in time by means of optical flow priors, and can be applied to wide-b...
Citació
Trulls, E.; Sanfeliu, A.; Moreno-Noguer, F. Spatiotemporal descriptor for wide-baseline stereo reconstruction of non-rigid and ambiguous scenes. A: European Conference on Computer Vision. "Computer Vision – ECCV 2012. Workshops and Demonstrations". Florència: Springer, 2012, p. 441-454.
Paraules clau
appearance descriptors, spatiotemporal, stereo
Grup de recerca
VIS - Visió Artificial i Sistemes Intel.ligents

Participants