On Utilising Template and Feature-Based Correspondence in Multi-view Appearance Models Export

@incollection{citeulike:1896342, abstract = {In principle, the recovery and reconstruction of a 3D object from its 2D view projections require the parameterisation of its shape structure and surface reflectance properties. Explicit representation and recovery of such 3D information is notoriously difficult to achieve. Alternatively, a linear combination of 2D views can be used which requires the establishment of dense correspondence between views. This in general, is difficult to compute and necessarily expensive. In this paper we examine the use of affine and local feature-based transformations in establishing correspondences between very large pose variations. In doing so, we utilise a generic-view template, a generic 3D surface model and Kernel PCA for modelling shape and texture nonlinearities across views. The abilities of both approaches to reconstruct and recover faces from any 2D image are evaluated and compared.}, author = {Romdhani, Sami and Psarrou, Alexandra and Gong, Shaogang}, citeulike-article-id = {1896342}, citeulike-linkout-0 = {http://www.springerlink.com/content/38bc9ye76ddkx02j}, journal = {Computer Vision - ECCV 2000}, keywords = {2\_5d, 2d, 3d, aam, kernal-pca, shape}, pages = {799--813}, posted-at = {2008-02-15 08:55:18}, priority = {2}, title = {On Utilising Template and Feature-Based Correspondence in Multi-view Appearance Models}, url = {http://www.springerlink.com/content/38bc9ye76ddkx02j}, year = {2000} }

TY - CHAP ID - citeulike:1896342 L3 - citeulike-article-id:1896342 N2 - In principle, the recovery and reconstruction of a 3D object from its 2D view projections require the parameterisation of its shape structure and surface reflectance properties. Explicit representation and recovery of such 3D information is notoriously difficult to achieve. Alternatively, a linear combination of 2D views can be used which requires the establishment of dense correspondence between views. This in general, is difficult to compute and necessarily expensive. In this paper we examine the use of affine and local feature-based transformations in establishing correspondences between very large pose variations. In doing so, we utilise a generic-view template, a generic 3D surface model and Kernel PCA for modelling shape and texture nonlinearities across views. The abilities of both approaches to reconstruct and recover faces from any 2D image are evaluated and compared. JF - Computer Vision - ECCV 2000 EP - 813 TI - On Utilising Template and Feature-Based Correspondence in Multi-view Appearance Models SP - 799 KW - 2_5d KW - 2d KW - 3d KW - aam KW - kernal-pca KW - shape AU - Romdhani, Sami AU - Psarrou, Alexandra AU - Gong, Shaogang PY - 2000/// UR - http://www.springerlink.com/content/38bc9ye76ddkx02j ER -