TY - EJOUR DO - 10.1109/TPAMI.2011.196 AB - Most 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. T1 - Monocular 3D Reconstruction of Locally Textured Surfaces IS - 6 DA - 2012 AU - Varol, Aydin AU - Shaji, Appu AU - Salzmann, Mathieu AU - Fua, Pascal JF - IEEE Transactions on Pattern Analysis and Machine Intelligence SP - 1118 - 1130 VL - 34 EP - 1118 - 1130 PB - Institute of Electrical and Electronics Engineers ID - 165831 KW - 3D Reconstruction KW - Shape KW - Shading SN - 0162-8828 UR - http://infoscience.epfl.ch/record/165831/files/top_1.pdf ER -