000146574 001__ 146574
000146574 005__ 20190316234735.0
000146574 02470 $$2ISI$$a000287728002226
000146574 037__ $$aCONF
000146574 245__ $$aPlenoptic based super-resolution for omnidirectional image sequences
000146574 260__ $$c2010
000146574 269__ $$a2010
000146574 336__ $$aConference Papers
000146574 520__ $$aThis paper addresses the reconstruction of high resolution omnidirectional images from a low resolution video acquired by an omnidirectional camera moving in a static scene. In order to exploit the additional information provided by the side images in the video sequence, the ego-motion of the camera must be accurately estimated in a first step. The reconstruction can then be modeled as a plenoptic sampling problem that has to encompass the change of viewpoint between each position of the omnidirectional sensor and the specific discretization of the real scene observed from each position. We formulate this problem as an ill-posed inverse problem that incorporates a regularization term based on a Total Variation (TV) prior. A graph variational formulation is used in order to ease the representation of omnidirectional data and to adapt the discretization of differential operators to the omnidirectional geometry. Experimental results on synthetic images demonstrate the relevance of this approach and its superiority compared to standard super-resolution using a single image.
000146574 6531_ $$aOmnidirectional
000146574 6531_ $$aGraph
000146574 6531_ $$aTotal Variation
000146574 6531_ $$aSuper-Resolution
000146574 6531_ $$aPlenoptic
000146574 6531_ $$aLTS2
000146574 6531_ $$aLTS4
000146574 700__ $$0242922$$g172333$$aBagnato, Luigi
000146574 700__ $$aBoursier, Yannick
000146574 700__ $$0241061$$g101475$$aFrossard, Pascal
000146574 700__ $$aVandergheynst, Pierre$$g120906$$0240428
000146574 7112_ $$dSeptember 26-29, 2010$$cHong Kong$$aIEEE International Conference on Image Processing (ICIP)
000146574 773__ $$tIEEE International Conference on Image Processing (ICIP)
000146574 8564_ $$uhttp://www.icip2010.org/$$zURL
000146574 8564_ $$uhttps://infoscience.epfl.ch/record/146574/files/ICIP2010_Poster.pdf$$zn/a$$s2130584
000146574 8564_ $$uhttps://infoscience.epfl.ch/record/146574/files/bagnato.pdf$$zn/a$$s541967
000146574 909C0 $$xU10380$$0252392$$pLTS2
000146574 909C0 $$pLTS4$$xU10851$$0252393
000146574 909CO $$qGLOBAL_SET$$pconf$$pSTI$$ooai:infoscience.tind.io:146574
000146574 917Z8 $$x172333
000146574 917Z8 $$x172333
000146574 917Z8 $$x172333
000146574 917Z8 $$x101475
000146574 917Z8 $$x101475
000146574 937__ $$aEPFL-CONF-146574
000146574 973__ $$rREVIEWED$$sPUBLISHED$$aEPFL
000146574 980__ $$aCONF