The highly-efficient surrogate energy is used to select among samples. Each predictor is conditioned on its ancestors, and generates a set of samples over a subset of the pose parameters. Our new framework, hierarchical sampling optimization, consists of a sequence of predictors organized into a kinematic hierarchy. In this paper, we show that we can significantly improving upon black box optimization by exploiting high-level knowledge of the structure of the parameters and using a local surrogate energy function.
This procedure knows little about either the relationships between the parameters or the form of the energy function. Typical approaches optimize an energy function over pose parameters using a 'black box' image generation procedure.
