000148055 001__ 148055
000148055 005__ 20190812205403.0
000148055 02470 $$2ISI$$a000287417501034
000148055 037__ $$aCONF
000148055 245__ $$aSimultaneous Point Matching and 3D Deformable Surface Reconstruction
000148055 269__ $$a2010
000148055 260__ $$bIeee Computer Soc Press, Customer Service Center, Po Box 3014, 10662 Los Vaqueros Circle, Los Alamitos, Ca 90720-1264 Usa$$c2010
000148055 336__ $$aConference Papers
000148055 490__ $$aIEEE Conference on Computer Vision and Pattern Recognition
000148055 520__ $$aIt has been shown that the 3D shape of a deformable surface in an image can be recovered by establishing correspondences between that image and a reference one in which the shape is known. These matches can then be used to set-up a convex optimization problem in terms of the shape parameters, which is easily solved. However, in many cases, the correspondences are hard to establish reliably. In this paper, we show that we can solve simultaneously for both 3D shape and correspondences, thereby using 3D shape constraints to guide the image matching and increasing robustness, for example when the textures are repetitive. This involves solving a mixed integer quadratic problem. While optimizing this problem is NP-hard in general, we show that its solution can nevertheless be approximated effectively by a branch-and-bound algorithm.
000148055 6531_ $$aComputer Vision
000148055 6531_ $$aDeformable Surfaces
000148055 6531_ $$a3D Reconstruction
000148055 700__ $$0245251$$g188751$$aShaji, Appu
000148055 700__ $$0242713$$g179178$$aVarol, Aydin
000148055 700__ $$aTorresani, Lorenzo
000148055 700__ $$aFua, Pascal$$g112366$$0240252
000148055 7112_ $$dJune 13-19, 2010$$cSan Francisco, U.S.A.$$a23rd IEEE Conference on Computer Vision and Pattern Recognition
000148055 773__ $$tProceedings of 23rd IEEE Conference on Computer Vision and Pattern Recognition
000148055 8564_ $$zn/a$$yn/a$$uhttps://infoscience.epfl.ch/record/148055/files/1292.pdf$$s9681032
000148055 909C0 $$xU10659$$pCVLAB$$0252087
000148055 909CO $$ooai:infoscience.tind.io:148055$$qGLOBAL_SET$$pconf$$pIC
000148055 937__ $$aEPFL-CONF-148055
000148055 973__ $$rREVIEWED$$sPUBLISHED$$aEPFL
000148055 980__ $$aCONF