Pose-normalized view synthesis from silhouettes

In this paper, we introduce an active view synthesis approachfrom silhouettes. With the virtual camera moving on a properly se-
lected 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 dis-
tance as the silhouette similarity measurement, this approach can
be used to generate the desired pose-normalized images for recog-
nition applications.