000219363 001__ 219363
000219363 005__ 20181203024245.0
000219363 0247_ $$2doi$$a10.1016/j.cviu.2015.11.004
000219363 022__ $$a1077-3142
000219363 02470 $$2ISI$$a000372378200015
000219363 037__ $$aARTICLE
000219363 245__ $$aTensor low-rank and sparse light field photography
000219363 260__ $$bElsevier$$c2016$$aSan Diego
000219363 269__ $$a2016
000219363 300__ $$a10
000219363 336__ $$aJournal Articles
000219363 520__ $$aHigh-quality light field photography has been one of the most difficult challenges in computational photography. Conventional methods either sacrifice resolution, use multiple devices, or require multiple images to be captured. Combining coded image acquisition and compressive reconstruction is one of the most promising directions to overcome limitations of conventional light field cameras. We present a new approach to compressive light field photography that exploits a joint tensor low-rank and sparse prior (LRSP) on natural light fields. As opposed to recently proposed light field dictionaries, our method does not require a computationally expensive learning stage but rather models the redundancies of high dimensional visual signals using a tensor low-rank prior. This is not only computationally more efficient but also more flexible in that the proposed techniques are easily applicable to a wide range of different imaging systems, camera parameters, and also scene types. (C) 2015 Elsevier Inc. All rights reserved.
000219363 6531_ $$aComputational photography
000219363 6531_ $$aLow-rank tensor factorization
000219363 6531_ $$aLow-rank and sparse decomposition
000219363 6531_ $$aCompressive sensing
000219363 700__ $$uEcole Polytech Fed Lausanne, Signal Proc Lab, CH-1015 Lausanne, Switzerland$$aKamal, Mandad Hosseini
000219363 700__ $$uMIT, Media Lab, Cambridge, MA 02139 USA$$aHeshmat, Barmak
000219363 700__ $$uMIT, Media Lab, Cambridge, MA 02139 USA$$aRaskar, Ramesh
000219363 700__ $$0240428$$g120906$$uEcole Polytech Fed Lausanne, Signal Proc Lab, CH-1015 Lausanne, Switzerland$$aVandergheynst, Pierre
000219363 700__ $$aWetzstein, Gordon
000219363 773__ $$j145$$tComputer Vision And Image Understanding$$q172-181
000219363 909C0 $$xU10380$$0252392$$pLTS2
000219363 909CO $$pSTI$$particle$$ooai:infoscience.tind.io:219363
000219363 917Z8 $$x120906
000219363 937__ $$aEPFL-ARTICLE-219363
000219363 973__ $$rREVIEWED$$sPUBLISHED$$aEPFL
000219363 980__ $$aARTICLE