000148800 001__ 148800
000148800 005__ 20190316234810.0
000148800 037__ $$aCONF
000148800 245__ $$aFast Structure from Motion for Planar Image Sequences
000148800 269__ $$a2010
000148800 260__ $$c2010
000148800 336__ $$aConference Papers
000148800 520__ $$aDense three-dimensional reconstruction of a scene from images is a challenging task. Usually, it is achieved by finding correspondences in successive images and computing the distance by means of epipolar geometry. In this paper, we propose a variational framework to solve the depth from motion problem for planar image sequences. We derive camera ego-motion estimation equations and we show how to combine the depth map and ego-motion estimation in a single algorithm. We successfully test our method on synthetic image sequences for general camera translation. Our method is highly parallelizable and thus well adapted for real-time implementation on the GPU.
000148800 6531_ $$aLTS2
000148800 6531_ $$aStructure from Motion
000148800 6531_ $$aVariational
000148800 6531_ $$aTV-L1
000148800 6531_ $$aGPGPU
000148800 700__ $$aWeishaupt, Andreas
000148800 700__ $$0242922$$aBagnato, Luigi$$g172333
000148800 700__ $$0240428$$aVandergheynst, Pierre$$g120906
000148800 7112_ $$a2010 European Signal Processing Conference$$cAalborg$$dAugust 23-27 2010
000148800 773__ $$tProceedings of Eusipco 2010
000148800 8564_ $$uhttp://www.eusipco2010.org/$$zURL
000148800 8564_ $$s2658554$$uhttps://infoscience.epfl.ch/record/148800/files/1569292715.pdf$$yPreprint$$zn/a
000148800 909C0 $$0252392$$pLTS2$$xU10380
000148800 909CO $$ooai:infoscience.tind.io:148800$$pconf$$pSTI$$qGLOBAL_SET
000148800 917Z8 $$x172333
000148800 917Z8 $$x172333
000148800 917Z8 $$x172333
000148800 937__ $$aEPFL-CONF-148800
000148800 973__ $$aEPFL$$rREVIEWED$$sPUBLISHED
000148800 980__ $$aCONF