000164033 001__ 164033
000164033 005__ 20180913060515.0
000164033 037__ $$aCONF
000164033 245__ $$aLarge occlusion completion using normal maps
000164033 269__ $$a2010
000164033 260__ $$c2010
000164033 336__ $$aConference Papers
000164033 520__ $$aDense disparity maps can be computed from wide-baseline stereo pairs but will inevitably contain large areas where the depth cannot be estimated accurately because the pixels are seen in one view only. A traditional approach to this problem is to introduce a global optimization scheme to fill-in the missing information by enforcing spatial-consistency, which usually means introducing a geometric regularization term that promotes smoothness. The world, however, is not necessarily smooth and we argue that a better approach is to monocularly estimate the surface normals and to use them to supply the required constraints. We will show that, even though the estimates are very rough, we nevertheless obtain more accurate depth-maps than by enforcing smoothness. Furthermore, this can be done effectively by solving large but sparse linear systems. 
000164033 6531_ $$aocclusion
000164033 6531_ $$adepthmap
000164033 6531_ $$astereo
000164033 700__ $$0242709$$aTola, Engin$$g170333
000164033 700__ $$aFossati, Andrea
000164033 700__ $$0244088$$aStrecha, Christoph$$g182325
000164033 700__ $$0240252$$aFua, Pascal$$g112366
000164033 7112_ $$aAsian Conference on Computer Vision$$cQueenstown, New Zealand$$dNovember 8-12, 2010
000164033 8564_ $$uhttp://cvlab.epfl.ch/~tola/publications.html$$zURL
000164033 8564_ $$s2507035$$uhttps://infoscience.epfl.ch/record/164033/files/normalcue.pdf$$yPublisher's version$$zn/a
000164033 909C0 $$0252087$$pCVLAB$$xU10659
000164033 909CO $$ooai:infoscience.tind.io:164033$$pconf$$pIC
000164033 917Z8 $$x170333
000164033 937__ $$aEPFL-CONF-164033
000164033 973__ $$aEPFL$$rREVIEWED$$sPUBLISHED
000164033 980__ $$aCONF