000200492 001__ 200492
000200492 005__ 20190316235947.0
000200492 022__ $$a1057-7149
000200492 0247_ $$2doi$$a10.1109/TIP.2017.2734567
000200492 037__ $$aARTICLE
000200492 245__ $$aWide-baseline object interpolation using shape prior regularization of epipolar plane images
000200492 269__ $$a2017
000200492 260__ $$c2017
000200492 336__ $$aJournal Articles
000200492 520__ $$aThis paper considers the synthesis of intermediate views of an object captured by two calibrated and widely spaced cameras. Based only on those two very different views, our paper proposes to reconstruct the object Epipolar Plane Image Volume [1] (EPIV), which describes the object transformation when continuously moving the viewpoint of the synthetic view in-between the two reference cameras. This problem is clearly ill-posed since the occlusions and the foreshortening effect make the reference views significantly different when the cameras are far apart. Our main contribution consists in disambiguating this ill-posed problem by constraining the interpolated views to be consistent with an object shape prior. This prior is learnt based on images captured by the two reference views, and consists in a nonlinear shape manifold representing the plausible silhouettes of the object described by Elliptic Fourier Descriptors. Experiments on both synthetic and natural images show that the proposed method preserves the topological structure of objects during the intermediate view synthesis, while dealing effectively with the self-occluded regions and with the severe foreshortening effect associated to wide-baseline camera configurations.
000200492 6531_ $$aWide-baseline matching
000200492 6531_ $$aimage-based rendering
000200492 6531_ $$aepipolar plane images
000200492 6531_ $$aview interpolation
000200492 6531_ $$afreeviewpoint
000200492 6531_ $$ashape priors.
000200492 700__ $$aVerleysen, Cédric
000200492 700__ $$aMaugey, Thomas
000200492 700__ $$0241061$$aFrossard, Pascal$$g101475
000200492 700__ $$aDe Vleeschouwer, Christophe
000200492 773__ $$j26$$k11$$q5477-5490$$tIEEE Transactions on Image Processing
000200492 8560_ $$falain.borel@epfl.ch
000200492 8564_ $$s13590188$$uhttps://infoscience.epfl.ch/record/200492/files/Src-Free_viewpoint_rendering.zip
000200492 8564_ $$s701623$$uhttps://infoscience.epfl.ch/record/200492/files/SupplementaryMaterial_TIP2015_WideBaselineShapePriors.pdf
000200492 8564_ $$s9738760$$uhttps://infoscience.epfl.ch/record/200492/files/TIP2015_WideBaselineShapePriors.pdf$$yn/a$$zn/a
000200492 8564_ $$s36808287$$uhttps://infoscience.epfl.ch/record/200492/files/Video_TIP2015_WideBaselineShapePriors.m4v
000200492 909C0 $$0252393$$pLTS4$$xU10851
000200492 909CO $$ooai:infoscience.tind.io:200492$$pSTI$$particle$$qGLOBAL_SET
000200492 917Z8 $$x206186
000200492 917Z8 $$x101475
000200492 917Z8 $$x101475
000200492 917Z8 $$x101475
000200492 917Z8 $$x101475
000200492 917Z8 $$x101475
000200492 937__ $$aEPFL-ARTICLE-200492
000200492 973__ $$aEPFL$$rREVIEWED$$sPUBLISHED
000200492 980__ $$aARTICLE