000188611 001__ 188611
000188611 005__ 20180913062016.0
000188611 020__ $$a978-0-8194-9708-6
000188611 0247_ $$2doi$$a10.1117/12.2023916
000188611 022__ $$a0277-786X
000188611 02470 $$2ISI$$a000326764600026
000188611 037__ $$aCONF
000188611 245__ $$aJoint image registration and reconstruction from compressed multi-view measurements
000188611 260__ $$aBellingham$$bSpie-Int Soc Optical Engineering$$c2013
000188611 269__ $$a2013
000188611 300__ $$a8
000188611 336__ $$aConference Papers
000188611 490__ $$aProceedings of SPIE
000188611 520__ $$aWe present a method for joint reconstruction of a set of images representing a given scene from few multi-view measurements obtained by compressed sensing. We model the correlation between measurements using global geometric transformations represented by few parameters. Then, we propose an algorithm able to jointly estimate these transformation parameters and the observed images from the available measurements. This method is also robust to occlusions appearing in the scene. The reconstruction algorithm minimizes a non-convex functional and generates a sequence of estimates converging to a critical point of this functional. Finally, we demonstrate the efficiency of the proposed method using numerical simulations.
000188611 6531_ $$aCompressed sensing
000188611 6531_ $$aImage registration
000188611 6531_ $$aIll-posed inverse problem
000188611 6531_ $$aNon-convex optimization
000188611 700__ $$0242927$$aPuy, Gilles$$g179918
000188611 700__ $$0240428$$aVandergheynst, Pierre$$g120906
000188611 7112_ $$aWavelets and Sparsity XV$$dAugust 26-29, 2013
000188611 773__ $$j8858$$tWavelets And Sparsity Xv
000188611 909C0 $$0252392$$pLTS2$$xU10380
000188611 909CO $$ooai:infoscience.tind.io:188611$$pconf$$pSTI
000188611 917Z8 $$x179918
000188611 937__ $$aEPFL-CONF-188611
000188611 973__ $$aEPFL$$rREVIEWED$$sPUBLISHED
000188611 980__ $$aCONF