Pose-Normalized View Synthesis From Silhouettes

Zhanfeng Yue, Rama Chellappa

Abstract: We introduce an active view synthesis approach from silhouettes. With the virtual camera moving on a properly selected circular trajectory around an object of interest, we achieve a collection of virtual views of the object, which is equivalent to the case that the object is on a rotating turntable and captured by a static camera whose optical axis is parallel to the turntable. We show how to derive the virtual camera's extrinsic parameters at each position on the trajectory. Using the turning function distance as the silhouette similarity measurement, this approach can be used to generate the desired pose-normalized images for recognition applications.