000231733 001__ 231733
000231733 005__ 20181203024836.0
000231733 0247_ $$2doi$$a10.1109/Tip.2017.2734567
000231733 022__ $$a1057-7149
000231733 02470 $$2ISI$$a000408817400008
000231733 037__ $$aARTICLE
000231733 245__ $$aWide-Baseline Foreground Object Interpolation Using Silhouette Shape Prior
000231733 260__ $$bIeee-Inst Electrical Electronics Engineers Inc$$c2017$$aPiscataway
000231733 269__ $$a2017
000231733 300__ $$a14
000231733 336__ $$aJournal Articles
000231733 520__ $$aWe consider the synthesis of intermediate views of an object captured by two widely spaced and calibrated cameras. This problem is challenging because foreshortening effects and occlusions induce significant differences between the reference images when the cameras are far apart. That makes the association or disappearance/appearance of their pixels difficult to estimate. Our main contribution lies in disambiguating this ill-posed problem by making the interpolated views consistent with a plausible transformation of the object silhouette between the reference views. This plausible transformation is derived from an object-specific prior that consists of a nonlinear shape manifold learned from multiple previous observations of this object by the two reference cameras. The prior is used to estimate the evolution of the epipolar silhouette segments between the reference views. This information directly supports the definition of epipolar silhouette segments in the intermediate views, as well as the synthesis of textures in those segments. It permits to reconstruct the epipolar plane images (EPIs) and the continuum of views associated with the EPI volume, obtained by aggregating the EPIs. Experiments on synthetic and natural images show that our method preserves the object topology in intermediate views and deals effectively with the self-occluded regions and the severe foreshortening effect associated with wide-baseline camera configurations.
000231733 6531_ $$aEpipolar plane image
000231733 6531_ $$alight-field
000231733 6531_ $$ashape prior
000231733 700__ $$uCatholic Univ Louvain, ISP Grp, ICTEAM Inst, B-1348 Louvain, Belgium$$aVerleysen, Cedric
000231733 700__ $$uINRIA, F-35042 Rennes, France$$aMaugey, Thomas
000231733 700__ $$0241061$$g101475$$aFrossard, Pascal
000231733 700__ $$uCatholic Univ Louvain, ISP Grp, ICTEAM Inst, B-1348 Louvain, Belgium$$aDe Vleeschouwer, Christophe
000231733 773__ $$j26$$tIeee Transactions On Image Processing$$k11$$q5477-5490
000231733 909C0 $$xU10851$$0252393$$pLTS4
000231733 909CO $$pSTI$$particle$$ooai:infoscience.tind.io:231733
000231733 917Z8 $$x101475
000231733 937__ $$aEPFL-ARTICLE-231733
000231733 973__ $$rREVIEWED$$sPUBLISHED$$aEPFL
000231733 980__ $$aARTICLE