In this work, we present a non-rigid approach to jointly solve the tasks of 2D-3D pose estimation and 2D image segmentation. In general, most frameworks that couple both pose estimation and segmentation assume that one has the exact knowledge of the 3D object. However, this assumption may be violated if only a general class to which a given shape belongs is given (e.g., cars, boats, or planes). Thus, we propose to solve the 2D-3D pose estimation and 2D image segmentation via nonlinear manifold learning of 3D embedded shapes for a class of objects for which one may not be able to associate a skeleton model. Thus, the novelty of our method is threefold: Firstly, we derive a generalized gradient flow for the task of non-rigid pose estimation and segmentation. Secondly, due to possible nonlinear structures in one's training set, we evolve the pre-image obtained through kernel PCA for the task of shape analysis. Thirdly, we show that the derivation for shape weights is general. This allows us to use various kernels with only minimal changes needed to be made to the overall evolution scheme. We provide experimental results that highlight the algorithm's robustness on challenging pose estimation and segmentation scenarios.


Linux - Operating Systems - Kernel - OpenSUSE - Linux kernel