Constructing implicit 3D shape models for pose estimation

We present a system that constructs “implicit shape models” for classes of rigid 3D objects and utilizes these models to estimating the pose of class instances in single 2D images. We use the framework of implicit shape models to construct a voting procedure that allows for 3D transformations and projection and accounts for self occlusion. The model is comprised of a collection of learned features, their 3D locations, their appearances in different views, and the set of views in which they are visible. We further learn the parameters of a model from training images by applying a method that relies on factorization. We demonstrate the utility of the constructed models by applying them in pose estimation experiments to recover the viewpoint of class instances.