000175391 001__ 175391
000175391 005__ 20190316235321.0
000175391 037__ $$aCONF
000175391 245__ $$aLight Field Tensor Recovery
000175391 269__ $$a2012
000175391 260__ $$c2012
000175391 336__ $$aConference Papers
000175391 520__ $$aThis paper presents a novel approach to capture light field in camera arrays based on the tensor recovery framework. Light fields are acquired by a linear array of cameras with overlapping field of view. We represent the light fields in shape of a tensor to exploit both local and non-local correlated structures of cameras image. The methodology is inspired by the recent research on matrix completion. We extend the affine matrix rank minimization to low-rank tensor recovery for light field acquisition, using a convex relaxation technique of the matrix rank. Finally, we develop a quantitative evaluation on a synthetic scene to assess our method with low-n-rank tensor recovery algorithm to assure the accuracy of our scheme with far less computational cost.
000175391 6531_ $$aLow-rank matrix recovery
000175391 6531_ $$aTensor recovery
000175391 6531_ $$aTrace Norm
000175391 6531_ $$aSVT algorithm
000175391 6531_ $$aLight fields
000175391 6531_ $$a&LTS2
000175391 700__ $$0244519$$g180513$$aHosseini Kamal, Mahdad
000175391 700__ $$aVandergheynst, Pierre$$0240428$$g120906
000175391 7112_ $$cOrlando, Florida, USA$$aIEEE International Conference on Image Processing
000175391 8564_ $$uhttps://infoscience.epfl.ch/record/175391/files/HossseiniKamal_ICIP2012.pdf$$zn/a$$s530710$$yn/a
000175391 909C0 $$xU10380$$0252392$$pLTS2
000175391 909CO $$qGLOBAL_SET$$pconf$$ooai:infoscience.tind.io:175391$$pSTI
000175391 917Z8 $$x180513
000175391 917Z8 $$x180513
000175391 937__ $$aEPFL-CONF-175391
000175391 973__ $$rREVIEWED$$sSUBMITTED$$aEPFL
000175391 980__ $$aCONF