000165831 001__ 165831
000165831 005__ 20190331192712.0
000165831 0247_ $$2doi$$a10.1109/TPAMI.2011.196
000165831 022__ $$a0162-8828
000165831 02470 $$2ISI$$a000302916600007
000165831 037__ $$aARTICLE
000165831 245__ $$aMonocular 3D Reconstruction of Locally Textured Surfaces
000165831 269__ $$a2012
000165831 260__ $$bInstitute of Electrical and Electronics Engineers$$c2012
000165831 336__ $$aJournal Articles
000165831 520__ $$aMost recent approaches to monocular non-rigid 3D shape recovery rely on exploiting point correspondences and work best when the whole surface is well-textured. The alternative is to rely either on contours or shading information, which has only been demonstrated in very restrictive settings. Here, we propose a novel approach to monocular deformable shape recovery that can operate under complex lighting and handle partially textured surfaces, whether developable or not. At the heart of our algorithm, are a learned mapping from intensity patterns to the shape of local surface patches and a principled approach to piecing together the resulting local shape estimates. We validate our approach quantitatively and qualitatively using both synthetic and real data.
000165831 6531_ $$a3D Reconstruction
000165831 6531_ $$aShape
000165831 6531_ $$aShading
000165831 700__ $$0242713$$g179178$$aVarol, Aydin
000165831 700__ $$0245251$$g188751$$aShaji, Appu
000165831 700__ $$aSalzmann, Mathieu
000165831 700__ $$aFua, Pascal$$g112366$$0240252
000165831 773__ $$j34$$tIEEE Transactions on Pattern Analysis and Machine Intelligence$$k6$$q1118-1130
000165831 8564_ $$uhttps://infoscience.epfl.ch/record/165831/files/top_1.pdf$$zn/a$$s2369429$$yn/a
000165831 909C0 $$xU10659$$0252087$$pCVLAB
000165831 909CO $$ooai:infoscience.tind.io:165831$$qGLOBAL_SET$$pIC$$particle
000165831 917Z8 $$x112366
000165831 917Z8 $$x179178
000165831 917Z8 $$x112366
000165831 917Z8 $$x112366
000165831 937__ $$aEPFL-ARTICLE-165831
000165831 973__ $$rREVIEWED$$sPUBLISHED$$aEPFL
000165831 980__ $$aARTICLE