000202076 001__ 202076
000202076 005__ 20190317000016.0
000202076 037__ $$aCONF
000202076 245__ $$aA Convex Solution to Disparity Estimation from Light Fields via the Primal-Dual Method
000202076 269__ $$a2014
000202076 260__ $$c2014
000202076 336__ $$aConference Papers
000202076 520__ $$aWe present a novel approach to the reconstruction of depth from light field data. Our method uses dictionary representations and group sparsity constraints to derive a convex formulation. Although our solution results in an increase of the problem dimensionality, we keep numerical complexity at bay by restricting the space of solutions and by exploiting an efficient Primal-Dual formulation. Comparisons with state of the art techniques, on both synthetic and real data, show promising performances.
000202076 6531_ $$aLight fields
000202076 6531_ $$amulti-view stereo
000202076 6531_ $$aprimal-dual formulation
000202076 700__ $$0244519$$aHosseini Kamal, Mahdad$$g180513
000202076 700__ $$aFavaro, Paolo
000202076 700__ $$0240428$$aVandergheynst, Pierre$$g120906
000202076 7112_ $$aEnergy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR)$$cHong Kong, China
000202076 8564_ $$s1270214$$uhttps://infoscience.epfl.ch/record/202076/files/Paper.pdf$$yn/a$$zn/a
000202076 8564_ $$s2156682$$uhttps://infoscience.epfl.ch/record/202076/files/Supplement.pdf
000202076 909C0 $$0252392$$pLTS2$$xU10380
000202076 909CO $$ooai:infoscience.tind.io:202076$$pconf$$pSTI$$qGLOBAL_SET
000202076 917Z8 $$x180513
000202076 917Z8 $$x180513
000202076 917Z8 $$x180513
000202076 917Z8 $$x180513
000202076 937__ $$aEPFL-CONF-202076
000202076 973__ $$aEPFL$$rREVIEWED$$sPUBLISHED
000202076 980__ $$aCONF