Carregant...
Carregant...

Vés al contingut (premeu Retorn)

An epipolar-constrained prior for efficient search in multi-view scenarios

Autor
Bosch, I.; Salvador, J.; Pérez-Pellitero, E.; Ruiz-Hidalgo, J.
Tipus d'activitat
Presentació treball a congrés
Nom de l'edició
22nd European Signal Processing Conference
Any de l'edició
2014
Data de presentació
2014-09-04
Llibre d'actes
2014 Proceedings of the 22nd European Signal Processing Conference (EUSIPCO): 1-5 September 2014: Lisbon, Portugal
Pàgina inicial
1667
Pàgina final
1671
Editor
Institute of Electrical and Electronics Engineers (IEEE)
Repositori
http://hdl.handle.net/2117/24818 Obrir en finestra nova
URL
http://ieeexplore.ieee.org/xpl/articleDetails.jsp?tp=&arnumber=6952613&queryText%3Dprior+for+efficient+search Obrir en finestra nova
Resum
In this paper we propose a novel framework for fast exploitation of multi-view cues with applicability in different image processing problems. In order to bring our proposed framework into practice, an epipolar-constrained prior is presented, onto which a random search algorithm is proposed to find good matches among the different views of the same scene. This algorithm includes a generalization of the local coherency in 2D images for multi-view wide-baseline cases. Experimental results show tha...
Citació
Bosch, I. [et al.]. An epipolar-constrained prior for efficient search in multi-view scenarios. A: European Signal Processing Conference. "2014 Proceedings of the 22nd European Signal Processing Conference (EUSIPCO): 1-5 September 2014: Lisbon, Portugal". Lisbon: Institute of Electrical and Electronics Engineers (IEEE), 2014, p. 1667-1671.
Paraules clau
Super Resolution, Deblurring, Epipolar Line, Approximate Nearest Neighbor
Grup de recerca
GPI - Grup de Processament d'Imatge i Vídeo

Participants

  • Bosch, Ignacio  (autor ponent)
  • Salvador, Jordi  (autor ponent)
  • Pérez Pellitero, Eduardo  (autor ponent)
  • Ruiz Hidalgo, Javier  (autor ponent)